{"id":13719,"url":"https://github.com/itouchz/awesome-deep-time-series-representations","name":"awesome-deep-time-series-representations","description":"[ACM CSUR] A curated list of papers on universal representation learning for time series.","projects_count":298,"last_synced_at":"2026-10-06T14:00:22.567Z","repository":{"id":216069673,"uuid":"468322115","full_name":"itouchz/awesome-deep-time-series-representations","owner":"itouchz","description":"[ACM CSUR] A curated list of papers on universal representation learning for time series.","archived":false,"fork":false,"pushed_at":"2026-08-16T14:36:10.000Z","size":2430,"stargazers_count":211,"open_issues_count":0,"forks_count":21,"subscribers_count":7,"default_branch":"main","last_synced_at":"2026-09-17T00:18:02.165Z","etag":null,"topics":["deep-learning","representation-learning","survey-paper","time-series","time-series-analysis"],"latest_commit_sha":null,"homepage":"https://itouchz.github.io/awesome-deep-time-series-representations/","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/itouchz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2022-03-10T11:54:04.000Z","updated_at":"2026-08-19T05:55:30.000Z","dependencies_parsed_at":"2024-04-08T17:07:25.762Z","dependency_job_id":"f5272695-903e-4f92-b1a7-299085f693b3","html_url":"https://github.com/itouchz/awesome-deep-time-series-representations","commit_stats":null,"previous_names":["itouchz/awesome-deep-time-series-representations"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/itouchz/awesome-deep-time-series-representations","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/itouchz%2Fawesome-deep-time-series-representations","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/itouchz%2Fawesome-deep-time-series-representations/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/itouchz%2Fawesome-deep-time-series-representations/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/itouchz%2Fawesome-deep-time-series-representations/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/itouchz","download_url":"https://codeload.github.com/itouchz/awesome-deep-time-series-representations/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/itouchz%2Fawesome-deep-time-series-representations/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":343170754,"owners_count":38087849,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-10-03T21:59:58.778Z","status":"online","status_checked_at":"2026-10-06T02:00:06.537Z","response_time":86,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-01-12T20:23:50.270Z","updated_at":"2026-10-06T14:00:22.567Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Relevant Studies on Open Challenges","Related Surveys (Latest Update: July, 2024)","Research Papers (Latest Update: NeurIPS 2024)","Related Surveys (Latest Update: October, 2023)","Research Papers (Latest Update: NeurIPS 2023)","Research Papers (Latest Update: KDD 2024)","Related Surveys (Latest Update: June, 2024)","Research Papers (Latest Update: ICML 2024)","Related Surveys (Latest Update: April, 2024)","Research Papers (Latest Update: ICLR 2024)","Related Surveys (Latest Update: May, 2024)","Proposed Taxonomy","Related Surveys (Latest Update: May, 2026)"],"sub_categories":["Time-Series Active Learning","Time-Series Data Mining and Analysis","Multi-Modal Representation Learning","Representation Learning","Neural Architectural Approaches","Data-Centric Approaches","Distribution Shifts and Adaptation","Learning-Focused Approaches","Reliable Data Augmentation","Neural Architecture Search (NAS)","Interpretability, Fairness, and Responsible Use"],"readme":"# Awesome Deep Time-Series Representations\n\nThis repository is intended to help readers interested in learning universal representations of time series with deep learning. \n\nSince the paper has been accepted by ACM Computing Surveys as the definitive version of record, we will update this repository regularly, in line with top-tier conference publication cycles, to keep it up to date _through **NeurIPS 2026**_. \nAfter that, if your paper is missing or you have other requests, please open an issue, submit a pull request, or contact patara.t@kaist.ac.kr\n\n\u003e Next Batch: IJCAI 2025, ICDM 2025, ICDE 2025, CIKM 2025, KDD 2025, ICML 2025, NeurIPS 2025 → NeurIPS 2026.\n\n![time-series representation learning framework](https://github.com/user-attachments/assets/8285d348-752c-430e-9815-b8f13bf5fa41)\n\n\n**Accompanying Paper**: [Universal Time-Series Representation Learning: A Survey](https://dl.acm.org/doi/10.1145/3817600), Extended Version on [arXiv](https://arxiv.org/abs/2401.03717).\n```bibtex\n@article{trirat2026universal,\n author = {Trirat, Patara and Shin, Yooju and Kang, Junhyeok and Nam, Youngeun and Na, Jihye and Bae, Minyoung and Kim, Joeun and Kim, Byunghyun and Lee, Jae-Gil},\n title = {Universal Time-Series Representation Learning: A Survey},\n year = {2026},\n issue_date = {September 2026},\n volume = {58},\n number = {12},\n doi = {10.1145/3817600},\n journal = {ACM Computing Surveys},\n month = jun,\n articleno = {321},\n numpages = {40}\n}\n```\n\n## Proposed Taxonomy\n\n![proposed taxonomy](https://github.com/user-attachments/assets/99145231-6674-4672-a701-e56c0c7a6f13)\n\n\n## Contents\n- [Related Survey Papers](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#related-surveys)\n - [Time-Series Data Mining and Analysis](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#time-series-data-mining-and-analysis)\n - [General Representation Learning](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#representation-learning)\n- [Research Papers](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#research-papers)\n - [Neural Architectural Approaches](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#neural-architectural-approaches)\n - [Learning-Focused Approaches](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#learning-focused-approaches)\n - [Data-Centric Approaches](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#data-centric-approaches)\n- [Relevant Studies on Open Challenges](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#relevant-studies-on-open-challenges)\n- [Other Repositories](https://github.com/itouchz/awesome-deep-time-series-representations/tree/main#neighbor-repositories)\n\n## Related Surveys (Latest Update: May, 2026)\n\n### Time-Series Data Mining and Analysis\n\n| **Title** | **Affiliation** | **Venue** | **Year** |\n| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- | ----------------------------------- | -------- |\n| [Discrete Wavelet Transform-based Time Series Analysis and Mining](https://dl.acm.org/doi/abs/10.1145/1883612.1883613) | University of Maryland | ACM CSUR | 2011 |\n| [Time-Series Data Mining](https://dl.acm.org/doi/10.1145/2379776.2379788) | IRCAM | ACM CSUR | 2012 |\n| [A Review of Unsupervised Feature Learning and Deep Learning for Time-Series Modeling](https://www.sciencedirect.com/science/article/pii/S0167865514000221) | Örebro University | Pattern Recognition Letters | 2014 |\n| [Time-series clustering – A decade review](https://www.sciencedirect.com/science/article/pii/S0306437915000733) | University of Malaya | Information Systems | 2015 |\n| [Deep Learning for Time-Series Analysis](https://arxiv.org/abs/1701.01887) | University of Kaiserslautern | arXiv | 2017 |\n| [A survey of methods for time series change point detection](https://link.springer.com/article/10.1007/s10115-016-0987-z) | Washington State University | KAIS | 2017 |\n| [Survey on time series motif discovery](https://wires.onlinelibrary.wiley.com/doi/full/10.1002/widm.1199) | Ostwestfalen-Lippe University of Applied Sciences | WIDM | 2017 |\n| [Wavelet Transform Application for/in Non-Stationary Time-Series Analysis: A Review](https://www.mdpi.com/2076-3417/9/7/1345) | Ecole Nationale des Sciences de l’Informatique | MDPI Applied Sciences | 2019 |\n| [Deep learning for time series classification: a review](https://link.springer.com/article/10.1007/s10618-019-00619-1) | Université Haute Alsace | Data Mining and Knowledge Discovery | 2019 |\n| [Anomaly Detection for IoT Time-Series Data: A Survey](https://ieeexplore.ieee.org/abstract/document/8926446) | University of Keele | IEEE IoT-J | 2019 |\n| [A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data](https://arxiv.org/abs/2010.12493) | Peking University | arXiv | 2020 |\n| [Approaches and Applications of Early Classification of Time Series: A Review](https://ieeexplore.ieee.org/abstract/document/9207873/) | Indian Institute of Technology (BHU) Varanasi | IEEE TAI | 2020 |\n| [A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series](https://arxiv.org/abs/2012.00168) | University of Massachusetts Amherst | NeurIPS Workshop on ML-RSA | 2020 |\n| [A Review of Deep Learning Models for Time Series Prediction](https://ieeexplore.ieee.org/document/8742529) | Dalian University of Technology | IEEE Sensors Journal | 2021 |\n| [An empirical survey of data augmentation for time series classification with neural networks](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0254841) | Kyushu University | PLOS ONE | 2021 |\n| [Time-series forecasting with deep learning: a survey](https://royalsocietypublishing.org/doi/full/10.1098/rsta.2020.0209) | University of Oxford | Phil.Trans.R.Soc.A | 2021 |\n| [A Review on Outlier/Anomaly Detection in Time Series Data](https://dl.acm.org/doi/abs/10.1145/3444690) | Basque Research and Technology Alliance | ACM CSUR | 2021 |\n| [A Review of Time-Series Anomaly Detection Techniques: A Step to Future Perspectives](https://link.springer.com/chapter/10.1007/978-3-030-73100-7_60) | University of Newcastle | FICC | 2021 |\n| [Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines](https://ieeexplore.ieee.org/abstract/document/9523565) | Seoul National University | IEEE Access | 2021 |\n| [Time Series Data Augmentation for Deep Learning: A Survey](https://www.ijcai.org/proceedings/2021/0631.pdf) | Alibaba Group | IJCAI | 2021 |\n| [An Experimental Review on Deep Learning Architectures for Time Series Forecasting](https://www.worldscientific.com/doi/abs/10.1142/S0129065721300011) | University of Sevilla | IJNS | 2021 |\n| [Experimental Comparison and Survey of Twelve Time Series Anomaly Detection Algorithms](https://jair.org/index.php/jair/article/view/12698) | Verint | JAIR | 2021 |\n| [Causal inference for time series analysis: problems, methods and evaluation](https://link.springer.com/article/10.1007/s10115-021-01621-0) | Arizona State University | KAIS | 2021 |\n| [End-to-end deep representation learning for time series clustering: a comparative study](https://link.springer.com/article/10.1007/s10618-021-00796-y) | Université de Haute Alsace | Data Mining and Knowledge Discovery | 2022 |\n| [Survey and Evaluation of Causal Discovery Methods for Time Series](https://www.jair.org/index.php/jair/article/view/13428) | Université Grenoble Alpes | JAIR | 2022 |\n| [A Review of Recurrent Neural Network-Based Methods in Computational Physiology](https://ieeexplore.ieee.org/abstract/document/9705533) | University of Pittsburgh | IEEE TNNLS | 2022 |\n| [Deep Learning for Time Series Anomaly Detection: A Survey](https://arxiv.org/abs/2211.05244) | Monash University | arXiv | 2022 |\n| [Deep Learning for Time Series Forecasting: Tutorial and Literature Survey](https://dl.acm.org/doi/full/10.1145/3533382) | Amazon Research | ACM CSUR | 2022 |\n| [Transformers in Time Series: A Survey](https://arxiv.org/abs/2202.07125) | Alibaba Group | IJCAI | 2023 |\n| [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://arxiv.org/abs/2302.02515) | Monash University | arXiv | 2023 |\n| [Label-efficient Time Series Representation Learning: A Review](https://arxiv.org/abs/2302.06433) | Nanyang Technological University | arXiv | 2023 |\n| [Neural Time Series Analysis with Fourier Transform: A Survey](https://arxiv.org/abs/2302.02173) | Beijing Institute of Technology | arXiv | 2023 |\n| [A Survey on Dimensionality Reduction Techniques for Time-Series Data](https://ieeexplore.ieee.org/document/10107391) | University of Colorado Boulder | IEEE Access | 2023 |\n| [Long sequence time-series forecasting with deep learning: A survey](https://www.sciencedirect.com/science/article/pii/S1566253523001355) | Southwest Jiaotong University | Information Fusion | 2023 |\n| [Data Augmentation techniques in time series domain: a survey and taxonomy](https://link.springer.com/article/10.1007/s00521-023-08459-3) | Universidad Politécnica de Madrid | Neural Computing \u0026 Applications | 2023 |\n| [Diffusion Models for Time Series Applications: A Survey](https://arxiv.org/abs/2305.00624) | University of Sydney | arXiv | 2023 |\n| [A Survey on Time-Series Pre-Trained Models](https://arxiv.org/abs/2305.10716) | South China University of Technology | arXiv | 2023 |\n| [Self-Supervised Contrastive Learning for Medical Time Series: A Systematic Review](https://www.mdpi.com/1424-8220/23/9/4221) | RMIT University | MDPI Sensors | 2023 |\n| [Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects](https://arxiv.org/abs/2306.10125) | Zhejiang University | IEEE TPAMI | 2024 |\n| [Unsupervised Representation Learning for Time Series: A Review](https://arxiv.org/abs/2308.01578) | Shandong University | arXiv | 2023 |\n| [Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook](https://arxiv.org/abs/2310.10196) | Monash University | arXiv | 2023 |\n| [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://arxiv.org/pdf/2403.14735.pdf) | The Hong Kong University of Science and Technology | arXiv | 2024 |\n| [Large Language Models for Time Series: A Survey](https://arxiv.org/pdf/2402.01801.pdf) | University of California, San Diego | arxiv | 2024 |\n| [Empowering Time Series Analysis with Large Language Models: A Survey](https://arxiv.org/pdf/2402.03182.pdf) | University of Connecticut | arxiv | 2024 |\n| [A Survey of Time Series Foundation Models: Generalizing Time Series Representation with Large Language Model](https://arxiv.org/abs/2405.02358) | Hong Kong University of Science and Technology | arxiv | 2024 |\n| [Position: What Can Large Language Models Tell Us about Time Series Analysis](https://openreview.net/forum?id=iroZNDxFJZ) | Griffith University, Chinese Academy of Sciences, The Hong Kong University of Science and Technology (Guangzhou) | ICML | 2024 |\n| [Deep Time Series Models: A Comprehensive Survey and Benchmark](https://ieeexplore.ieee.org/abstract/document/11509648) | Tsinghua University | IEEE TPAMI | 2026 |\n| [Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey](https://arxiv.org/abs/2405.02358) | The Hong Kong University of Science and Technology (Guangzhou) | arXiv | 2024 |\n| [Multi-modal Time Series Analysis: A Tutorial and Survey](https://dl.acm.org/doi/abs/10.1145/3711896.3736567) | University of Connecticut | KDD | 2025 |\n| [Foundation Models for Time Series: A Survey](https://arxiv.org/abs/2504.04011) | Dell Technologies | arXiv | 2025 |\n| [How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook](https://arxiv.org/abs/2503.11835) | Georgia Institute of Technology | arXiv | 2025 | \n| [Out-of-Distribution Generalization in Time Series: A Survey](https://www.sciencedirect.com/science/article/abs/pii/S1566253526002150) | Southwest Jiaotong University | Information Fusion | 2026 |\n| [Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models](https://arxiv.org/abs/2503.11411) | Salesforce AI Research | arXiv | 2025 |\n\n\n### Representation Learning\n\n| **Title** | **Affiliation** | **Venue** | **Year** |\n| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------- | ------------------------------- | -------- |\n| [Representation Learning: A Review and New Perspectives](https://ieeexplore.ieee.org/document/6472238) | University of Montreal | IEEE TPAMI | 2013 |\n| [A Survey of Multi-View Representation Learning](https://ieeexplore.ieee.org/abstract/document/8471216) | Zhejiang University | IEEE TKDE | 2019 |\n| [Deep Multimodal Representation Learning: A Survey](https://ieeexplore.ieee.org/abstract/document/8715409/) | Fuzhou University | IEEE Access | 2019 |\n| [A Survey on Representation Learning for User Modeling](https://www.ijcai.org/proceedings/2020/0695.pdf) | University of Georgia | IJCAI | 2020 |\n| [A survey on deep geometry learning: From a representation perspective](https://link.springer.com/article/10.1007/s41095-020-0174-8) | Chinese Academy of Sciences | Computational Visual Media | 2020 |\n| [A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications](https://ieeexplore.ieee.org/document/9043500/) | Xiamen University | IEEE Access | 2020 |\n| [Contrastive Representation Learning: A Framework and Review](https://ieeexplore.ieee.org/abstract/document/9226466) | Dublin City University | IEEE Access | 2020 |\n| [Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data](https://arxiv.org/abs/2206.02353) | RMIT University | arXiv | 2022 |\n| [Self-Supervised Representation Learning: Introduction, advances, and challenges](https://ieeexplore.ieee.org/abstract/document/9770283) | University of Edinburgh | IEEE Signal Processing Magazine | 2022 |\n| [A Brief Overview of Universal Sentence Representation Methods: A Linguistic View](https://dl.acm.org/doi/10.1145/3482853) | KU Leuven | ACM CSUR | 2022 |\n| [Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding](https://dl.acm.org/doi/full/10.1145/3491206) | Soochow University | ACM CSUR | 2022 |\n| [Evaluation Methods for Representation Learning: A Survey](https://www.ijcai.org/proceedings/2022/0776.pdf) | University of Tokyo | IJCAI | 2022 |\n| [Self-Supervised Speech Representation Learning: A Review](https://ieeexplore.ieee.org/abstract/document/9893562) | Meta | IEEE JSTSP | 2022 |\n| [A Survey on Hypergraph Representation Learning](https://dl.acm.org/doi/abs/10.1145/3605776) | Università degli Studi di Torino | ACM CSUR | 2023 |\n| [Representation learning for knowledge fusion and reasoning in Cyber–Physical–Social Systems: Survey and perspectives](https://www.sciencedirect.com/science/article/pii/S156625352200135X) | Hainan University | Information Fusion | 2023 |\n| [Survey of Deep Representation Learning for Speech Emotion Recognition](https://ieeexplore.ieee.org/abstract/document/9543566) | University of Southern Queensland | IEEE TAFFC | 2023 |\n| [Graph Representation Learning and Its Applications: A Survey](https://www.mdpi.com/1424-8220/23/8/4168) | Catholic University of Korea | MDPI Sensors | 2023 |\n| [Graph Representation Learning Meets Computer Vision: A Survey](https://ieeexplore.ieee.org/abstract/document/9844822) | Xidian University | IEEE TAI | 2023 |\n| [A Comprehensive Survey on Deep Graph Representation Learning](https://arxiv.org/abs/2304.05055) | Peking University | arXiv | 2023 |\n| [Dynamic Graph Representation Learning with Neural Networks: A Survey](https://arxiv.org/abs/2304.05729) | University of Rouen Normandy | arXiv | 2023 |\n| [Multiscale Representation Learning for Image Classification: A Survey](https://ieeexplore.ieee.org/abstract/document/9650759) | Xidian University | IEEE TAI | 2023 |\n| [A Survey on Protein Representation Learning: Retrospect and Prospect](https://arxiv.org/abs/2301.00813) | Westlake University | arXiv | 2023 |\n\n\n## Research Papers (Latest Update: NeurIPS 2024)\n\n### Data-Centric Approaches\n![examples of data-centric approaches](https://github.com/user-attachments/assets/7f452a09-b273-4b19-998f-c349d7376e49)\n\n\u003e This group presents the methods that focus on finding a new way to enhance the usefulness of the _training data_ at hand. These approaches prioritize engineering the data itself rather than focusing on model architecture and loss function design to capture the underlying patterns, trends, and relevant features within the time series. As in the figure, we categorize these data-centric approaches into two groups based on their objectives: improving data quality or increasing data quantity.\n\n| Year | Title | Venue |\n| ---- | ----- | ----- |\n| 2018 | [](https://dl.acm.org/doi/abs/10.1145/3219819.3220060)[Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis](https://dl.acm.org/doi/abs/10.1145/3219819.3220060) | KDD |\n| 2019 | [](https://proceedings.neurips.cc/paper_files/paper/2019/hash/53c6de78244e9f528eb3e1cda69699bb-Abstract.html)[Unsupervised Scalable Representation Learning for Multivariate Time Series](https://proceedings.neurips.cc/paper_files/paper/2019/hash/53c6de78244e9f528eb3e1cda69699bb-Abstract.html) | NeurIPS |\n| 2021 | [](https://www.sciencedirect.com/science/article/pii/S0020025520312287)[A deep multi-task representation learning method for time series classification and retrieval](https://www.sciencedirect.com/science/article/pii/S0020025520312287) | Information Sciences |\n| 2021 | [](https://openreview.net/forum?id=txWfwhc6gi)[Contrastive Learning of Global and Local Video Representations](https://openreview.net/forum?id=txWfwhc6gi) | NeurIPS |\n| 2021 | [](https://www.sciencedirect.com/science/article/pii/S0950705120306808)[DeLTa: Deep local pattern representation for time-series clustering and classification using visual perception](https://www.sciencedirect.com/science/article/pii/S0950705120306808) | KBS |\n| 2022 | [](https://ojs.aaai.org/index.php/AAAI/article/view/20210)[Cross-Modal Mutual Learning for Audio-Visual Speech Recognition and Manipulation](https://ojs.aaai.org/index.php/AAAI/article/view/20210) | AAAI |\n| 2022 | [](https://openaccess.thecvf.com/content/CVPR2022/html/Chen_Frame-Wise_Action_Representations_for_Long_Videos_via_Sequence_Contrastive_Learning_CVPR_2022_paper.html)[Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning](https://openaccess.thecvf.com/content/CVPR2022/html/Chen_Frame-Wise_Action_Representations_for_Long_Videos_via_Sequence_Contrastive_Learning_CVPR_2022_paper.html) | CVPR |\n| 2022 | [](https://openaccess.thecvf.com/content/WACV2022/html/Zhang_Hierarchically_Decoupled_Spatial-Temporal_Contrast_for_Self-Supervised_Video_Representation_Learning_WACV_2022_paper.html)[Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning](https://openaccess.thecvf.com/content/WACV2022/html/Zhang_Hierarchically_Decoupled_Spatial-Temporal_Contrast_for_Self-Supervised_Video_Representation_Learning_WACV_2022_paper.html) | WACV |\n| 2022 | [](https://arxiv.org/abs/2210.10630)[Irregularly-Sampled Time Series Modeling with Spline Networks](https://arxiv.org/abs/2210.10630) | ICML (Workshop) |\n| 2022 | [](https://ieeexplore.ieee.org/document/9769928)[Multi-View Integrative Attention-Based Deep Representation Learning for Irregular Clinical Time-Series Data](https://ieeexplore.ieee.org/document/9769928) | IEEE JBHI |\n| 2022 | [](https://openreview.net/forum?id=OJ4mMfGKLN)[Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://openreview.net/forum?id=OJ4mMfGKLN) | NeurIPS |\n| 2022 | [](https://www.sciencedirect.com/science/article/abs/pii/S0950705122002726)[TimeCLR: A self-supervised contrastive learning framework for univariate time series representation](https://www.sciencedirect.com/science/article/abs/pii/S0950705122002726) | KBS |\n| 2022 | [](https://proceedings.mlr.press/v162/yang22e.html)[Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion](https://proceedings.mlr.press/v162/yang22e.html) | ICML |\n| 2023 | [](https://dl.acm.org/doi/10.1145/3583780.3614759)[A Co-training Approach for Noisy Time Series Learning](https://dl.acm.org/doi/10.1145/3583780.3614759) | CIKM |\n| 2023 | [](https://ojs.aaai.org/index.php/AAAI/article/view/25915)[Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling](https://ojs.aaai.org/index.php/AAAI/article/view/25915) | AAAI |\n| 2023 | [](https://arxiv.org/abs/2310.11959)[A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis](https://arxiv.org/abs/2310.11959) | VLDB |\n| 2023 | [](https://openreview.net/forum?id=fxjzKOdw9wb)[Exploring Temporally Dynamic Data Augmentation for Video Recognition](https://openreview.net/forum?id=fxjzKOdw9wb) | ICLR |\n| 2023 | [](https://ojs.aaai.org/index.php/AAAI/article/view/25194)[Frequency Selective Augmentation for Video Representation Learning](https://ojs.aaai.org/index.php/AAAI/article/view/25194) | AAAI |\n| 2023 | [](https://openaccess.thecvf.com/content/CVPR2023/html/Zhao_Learning_Video_Representations_From_Large_Language_Models_CVPR_2023_paper.html)[Learning Video Representations From Large Language Models](https://openaccess.thecvf.com/content/CVPR2023/html/Zhao_Learning_Video_Representations_From_Large_Language_Models_CVPR_2023_paper.html) | CVPR |\n| 2023 | [](https://openreview.net/forum?id=5lgD4vU-l24s)[Recursive Time Series Data Augmentation](https://openreview.net/forum?id=5lgD4vU-l24s) | ICLR |\n| 2023 | [](https://ojs.aaai.org/index.php/AAAI/article/view/25575)[Time Series Contrastive Learning with Information-Aware Augmentations](https://ojs.aaai.org/index.php/AAAI/article/view/25575) | AAAI |\n| 2023 | [](https://openreview.net/pdf?id=EvGOdASdHi)[Context Consistency Regularization for Label Sparsity in Time Series](https://openreview.net/pdf?id=EvGOdASdHi) | ICML |\n| 2023 | [](https://openreview.net/forum?id=dbVRDk2wt7)[Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning](https://openreview.net/forum?id=dbVRDk2wt7) | NeurIPS |\n| 2024 | [](https://arxiv.org/pdf/2306.06579)[Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder](https://arxiv.org/pdf/2306.06579) | ICDM |\n| 2024 | [](https://openreview.net/forum?id=bWcnvZ3qMb)[FITS: MODELING TIME SERIES WITH 10k PARAMETERS](https://openreview.net/forum?id=bWcnvZ3qMb) | ICLR |\n| 2024 | [](https://arxiv.org/abs/2312.15709)[TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://arxiv.org/abs/2312.15709) | AAAI |\n| 2024 | [](https://openreview.net/forum?id=EIPLdFy3vp)[PARAMETRIC AUGMENTATION FOR TIME SERIES CONTRASTIVE LEARNING](https://openreview.net/forum?id=EIPLdFy3vp) | ICLR |\n| 2024 | [](https://openreview.net/forum?id=bYRYb7DMNo)[Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://openreview.net/forum?id=bYRYb7DMNo) | ICML |\n| 2024 | [](https://openreview.net/forum?id=ecO7WOIlMD)[MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series](https://openreview.net/forum?id=ecO7WOIlMD) | ICML |\n| 2024 | [](https://openreview.net/forum?id=FVvf69a5rx)[MOMENT: A Family of Open Time-series Foundation Models](https://openreview.net/forum?id=FVvf69a5rx) | ICML |\n| 2024 | [](https://arxiv.org/abs/2405.10597)[UniCL: A Universal Contrastive Learning Framework for Large Time Series Models](https://arxiv.org/abs/2405.10597) | arXiv |\n| 2024 | [](https://openreview.net/forum?id=5iUxMVJVEV\u0026noteId=fDQ5hBvom8)[Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis](https://openreview.net/forum?id=5iUxMVJVEV\u0026noteId=fDQ5hBvom8) | NeurIPS |\n| 2024 | [](https://dl.acm.org/doi/pdf/10.1145/3627673.3679699)[Time-Series Representation Learning via Dual Reference Contrasting](https://dl.acm.org/doi/pdf/10.1145/3627673.3679699) | CIKM |\n| 2025 | [](https://arxiv.org/abs/2412.11376)[ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://arxiv.org/abs/2412.11376) | AAAI |\n| 2025 | [](https://arxiv.org/abs/2412.20790)[Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning](https://arxiv.org/abs/2412.20790) | AAAI |\n| 2025 | [](https://dl.acm.org/doi/10.1145/3696410.3714931)[Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals](https://dl.acm.org/doi/10.1145/3696410.3714931) | WWW |\n| 2025 | [](https://openreview.net/forum?id=1CLzLXSFNn)[TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis](https://openreview.net/forum?id=1CLzLXSFNn) | ICLR |\n\n\n### Neural Architectural Approaches\n![examples of neural architectural approaches](https://github.com/user-attachments/assets/d276609c-d187-407e-8ca4-2e3da9bf7f20)\n\n\u003e As neural architectures play a crucial role in the quality of representations, this group examines novel _network architecture_ designs aimed at enhancing representation learning. These improvements (depicted in the figure) include, for example, better temporal modeling, handling missing values and irregularities, and extracting inter-variable dependencies in multivariate time series.\n\n| Year | Title | Venue |\n| ---- | ----- | ----- |\n| 2018 | [](https://www.sciencedirect.com/science/article/abs/pii/S0031320319302766)[Learning representations of multivariate time series with missing data](https://www.sciencedirect.com/science/article/abs/pii/S0031320319302766) | Pattern Recognition |\n| 2018 | [](https://dl.acm.org/doi/abs/10.1145/3219819.3220060)[Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis](https://dl.acm.org/doi/abs/10.1145/3219819.3220060) | KDD |\n| 2019 | [](https://ieeexplore.ieee.org/document/8736337)[Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representation](https://ieeexplore.ieee.org/document/8736337) | IEEE/ACM TASLP |\n| 2019 | [](https://papers.nips.cc/paper_files/paper/2019/hash/42a6845a557bef704ad8ac9cb4461d43-Abstract.html)[Latent ODEs for Irregularly-Sampled Time Series](https://papers.nips.cc/paper_files/paper/2019/hash/42a6845a557bef704ad8ac9cb4461d43-Abstract.html) | NeurIPS |\n| 2019 | [](https://link.springer.com/chapter/10.1007/978-3-030-46133-1_19)[Learning Disentangled Representations of Satellite Image Time Series](https://link.springer.com/chapter/10.1007/978-3-030-46133-1_19) | ECML PKDD |\n| 2019 | [](https://dl.acm.org/doi/10.1145/3357384.3358155)[Towards Explainable Representation of Time-Evolving Graphs via Spatial-Temporal Graph Attention Networks](https://dl.acm.org/doi/10.1145/3357384.3358155) | CIKM |\n| 2019 | [](https://proceedings.neurips.cc/paper_files/paper/2019/hash/53c6de78244e9f528eb3e1cda69699bb-Abstract.html)[Unsupervised Scalable Representation Learning for Multivariate Time Series](https://proceedings.neurips.cc/paper_files/paper/2019/hash/53c6de78244e9f528eb3e1cda69699bb-Abstract.html) | NeurIPS |\n| 2020 | [](https://ieeexplore.ieee.org/iel7/76/4358651/09051710.pdf)[A real-time action representation with temporal encoding and deep compression](https://ieeexplore.ieee.org/iel7/76/4358651/09051710.pdf) | IEEE TCSVT |\n| 2020 | [](https://ieeexplore.ieee.org/document/8685795)[End-to-End Incomplete Time-Series Modeling From Linear Memory of Latent Variables](https://ieeexplore.ieee.org/document/8685795) | IEEE TCYB |\n| 2020 | [](https://link.springer.com/chapter/10.1007/978-3-030-58580-8_19)[Memory-Augmented Dense Predictive Coding for Video Representation Learning](https://link.springer.com/chapter/10.1007/978-3-030-58580-8_19) | ECCV |\n| 2020 | [](https://link.springer.com/chapter/10.1007/978-3-030-58517-4_10)[Temporal Aggregate Representations for Long-Range Video Understanding](https://link.springer.com/chapter/10.1007/978-3-030-58517-4_10) | ECCV |\n| 2021 | [](https://www.sciencedirect.com/science/article/pii/S0020025520312287)[A deep multi-task representation learning method for time series classification and retrieval](https://www.sciencedirect.com/science/article/pii/S0020025520312287) | Information Sciences |\n| 2021 | [](https://dl.acm.org/doi/10.1145/3447548.3467401)[A Transformer-based Framework for Multivariate Time Series Representation Learning](https://dl.acm.org/doi/10.1145/3447548.3467401) | KDD |\n| 2021 | [](https://ieeexplore.ieee.org/abstract/document/9679144)[Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting](https://ieeexplore.ieee.org/abstract/document/9679144) | ICDM |\n| 2021 | [](https://www.sciencedirect.com/science/article/pii/S0950705120306808)[DeLTa: Deep local pattern representation for time-series clustering and classification using visual perception](https://www.sciencedirect.com/science/article/pii/S0950705120306808) | KBS |\n| 2021 | [](https://openreview.net/forum?id=4c0J6lwQ4_)[Multi-Time Attention Networks for Irregularly Sampled Time Series](https://openreview.net/forum?id=4c0J6lwQ4_) | ICLR |\n| 2021 | [](https://openaccess.thecvf.com/content/CVPR2021/html/Guo_SSAN_Separable_Self-Attention_Network_for_Video_Representation_Learning_CVPR_2021_paper.html)[SSAN: Separable Self-Attention Network for Video Representation Learning](https://openaccess.thecvf.com/content/CVPR2021/html/Guo_SSAN_Separable_Self-Attention_Network_for_Video_Representation_Learning_CVPR_2021_paper.html) | CVPR |\n| 2021 | [](https://www.ijcai.org/proceedings/2021/414)[TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data](https://www.ijcai.org/proceedings/2021/414) | IJCAI |\n| 2021 | [](https://ojs.aaai.org/index.php/AAAI/article/view/16846)[Time Series Domain Adaptation via Sparse Associative Structure Alignment](https://ojs.aaai.org/index.php/AAAI/article/view/16846) | AAAI |\n| 2021 | [](https://proceedings.neurips.cc/paper_files/paper/2021/hash/51200d29d1fc15f5a71c1dab4bb54f7c-Abstract.html)[TriBERT: Human-centric Audio-visual Representation Learning](https://proceedings.neurips.cc/paper_files/paper/2021/hash/51200d29d1fc15f5a71c1dab4bb54f7c-Abstract.html) | NeurIPS |\n| 2022 | [](https://arxiv.org/abs/2212.03560)[CrossPyramid: Neural Ordinary Differential Equations Architecture for Partially-observed Time-series](https://arxiv.org/abs/2212.03560) | arXiv |\n| 2022 | [](https://proceedings.mlr.press/v151/tonekaboni22a.html)[Decoupling Local and Global Representations of Time Series](https://proceedings.mlr.press/v151/tonekaboni22a.html) | AISTATS |\n| 2022 | [](https://dl.acm.org/doi/abs/10.1145/3485447.3512030)[EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting](https://dl.acm.org/doi/abs/10.1145/3485447.3512030) | WWW |\n| 2022 | [](https://openreview.net/forum?id=DZ2FaoMhWRb)[HyperTime: Implicit Neural Representations for Time Series](https://openreview.net/forum?id=DZ2FaoMhWRb) | NeurIPS (Workshop) |\n| 2022 | [](https://dl.acm.org/doi/abs/10.1145/3511808.3557386)[MARINA: An MLP-Attention Model for Multivariate Time-Series Analysis](https://dl.acm.org/doi/abs/10.1145/3511808.3557386) | CIKM |\n| 2022 | [](https://proceedings.mlr.press/v162/schirmer22a.html)[Modeling Irregular Time Series with Continuous Recurrent Units](https://proceedings.mlr.press/v162/schirmer22a.html) | ICML |\n| 2022 | [](https://dl.acm.org/doi/10.1145/3534678.3539329)[TARNet : Task-Aware Reconstruction for Time-Series Transformer](https://dl.acm.org/doi/10.1145/3534678.3539329) | KDD |\n| 2022 | [](https://ieeexplore.ieee.org/abstract/document/9713748)[TCGL: Temporal Contrastive Graph for Self-Supervised Video Representation Learning](https://ieeexplore.ieee.org/abstract/document/9713748) | IEEE TIP |\n| 2022 | [](https://dl.acm.org/doi/abs/10.1145/3534678.3539140)[Towards Learning Disentangled Representations for Time Series](https://dl.acm.org/doi/abs/10.1145/3534678.3539140) | KDD |\n| 2022 | [](https://proceedings.mlr.press/v162/yang22e.html)[Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion](https://proceedings.mlr.press/v162/yang22e.html) | ICML |\n| 2022 | [](https://ieeexplore.ieee.org/document/9878692/)[Weakly Paired Associative Learning for Sound and Image Representations via Bimodal Associative Memory](https://ieeexplore.ieee.org/document/9878692/) | CVPR |\n| 2023 | [](https://www.vldb.org/pvldb/vol17/p386-wang.pdf)[A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning](https://www.vldb.org/pvldb/vol17/p386-wang.pdf) | VLDB |\n| 2023 | [](https://openreview.net/forum?id=sOQBHlCmzp)[Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series](https://openreview.net/forum?id=sOQBHlCmzp) | NeurIPS |\n| 2023 | [](https://openreview.net/forum?id=YJDz4F2AZu)[ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling](https://openreview.net/forum?id=YJDz4F2AZu) | NeurIPS |\n| 2023 | [](https://dl.acm.org/doi/abs/10.1145/3583780.3615097)[TriD-MAE: A Generic Pre-trained Model for Multivariate Time Series with Missing Values](https://dl.acm.org/doi/abs/10.1145/3583780.3615097) | CIKM |\n| 2023 | [](https://arxiv.org/abs/2310.11959)[A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis](https://arxiv.org/abs/2310.11959) | VLDB |\n| 2023 | [](https://arxiv.org/pdf/2311.14782)[One Fits All: Universal Time Series Analysis by Pretrained LM and Specially Designed Adaptors](https://arxiv.org/pdf/2311.14782) | arXiv |\n| 2023 | [](https://openreview.net/forum?id=2EpjkjzdCAa)[Effectively Modeling Time Series with Simple Discrete State Spaces](https://openreview.net/forum?id=2EpjkjzdCAa) | ICLR |\n| 2023 | [](https://pdf.sciencedirectassets.com/271505/1-s2.0-S0950705123X00161/1-s2.0-S0950705123005403/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEF8aCXVzLWVhc3QtMSJIMEYCIQD5hn8Mnl3gtFxq1nUFNfN4AkRGLGc0J7neyhwNqErOWgIhAPaV8bgoej7W9FIVIXRJEs1dJ4VCrxcjrjGRBp%2BkzRHlKrIFCBgQBRoMMDU5MDAzNTQ2ODY1IgyE6HLDOC7UTDUg0pkqjwUea8WEnsKUVN0tQyNMW2CZ0gIGG2DL4zI%2FOhz0UeagODZquX58pQLjvbMX9m5ohgzmh3UXgw6NklEoIDfnrs9%2BmRAiI0kOhB3SKGMmpYneL5TfxmSpLp51G53KC9usiYRZcxWti99qQVxTizvMEB8aaidOw7buJpMFN5%2FqZqNED0VGiTjIXh37Vs7kWfZ93M5ADP27q%2F4RwvixEekWumRgoOZr4JmpCAhgIAvdxT3A4Va%2BO4IHfqloPut4mBeFQflTBaF1VXEWGY2nKQNfvnjOvpk6jWIBrIkE4PCkDjPQVglUCVFbtkYn37DoEM6qz5o%2FJxDNT3fxyDMsJyzPqV4WJ6W22FoHjkXF4zUEOsJpwBiuAdwBQy5ej6%2BItgLt7p4Q%2BkhYpn%2F4Zdw8pn%2BPrhKVoI5%2B2NmePKc9xu9XSvh%2B%2F7oVotJArmAmeNiSl%2BNf4R848MQ%2Bilmg5MeeHbIFWJc2QGxFDOTWKJsds9yIgMfZIVMUzd2anx4MHvT6lW4qdFKXb9nxZj0%2BANXq2dyCMMUD4Bg5q6OzYJZsRkK3p6Bwh80m%2BAIDIzy6ze2KKpoLYs3eDniVHtZJJNL%2FjFUepIVM0QpaYF5bj1fODRi4MUGE%2B%2BR56LZ4LJdDZTqQV%2B1De9VNPmBJV7%2B8OHjSdI48agJ7kKg%2B30Cradn3xXPkiL6cXuRxuePwCcacJ8sNyVVEPJXK2W2tKYH8IuVm4GdAM1Q%2BmYMxpJzDsPE08FNN8AZ6n4ezHtoWHdxay6WzaiWpLOEKYaoDRHALfTuwsen3FtEqXFECsPYlPjDR6tH4Nndku4pfjw90CI7es4ggMqUoxzU8cbbojdDG%2FmOaeKztu7fQqDJGD9Z3mY9jJYxNs1HBMMLQ46YGOrABXQddNJuWvlRrRFyMKs%2FyWrIKde1VETUwdPd5o6xsXQOIqXtJaAt5zbDTfYMXJ9Mz0KiEkkE5Dayt33ozxrR9KKzYxKUtsd67zB3EWac8De%2FOX62MGAQCXlvYlVijjVPosfJXFvB7zD%2BKIppS7RUYYDpNqcW8DOQUDIOuSnk1VG3fVCDU88o81OBr2ZF%2Btt4mo8FyTK%2BgX0gmeMG%2BP1B1eZwglxj82329ZvmAEFv11ns%3D\u0026X-Amz-Algorithm=AWS4-HMAC-SHA256\u0026X-Amz-Date=20230813T153436Z\u0026X-Amz-SignedHeaders=host\u0026X-Amz-Expires=300\u0026X-Amz-Credential=ASIAQ3PHCVTYVHIZFQJK%2F20230813%2Fus-east-1%2Fs3%2Faws4_request\u0026X-Amz-Signature=edd52e1a7e3d9453d4620d4f1602656da03fadd4a82d3d5af1dc3e3ba8d45d32\u0026hash=c29b8e0b4587df019b2d07326b7a707d3765b18585be1a37c4047e8a4f6c5ebf\u0026host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61\u0026pii=S0950705123005403\u0026tid=spdf-df89dd41-6329-4760-8dc8-84cd1d0071f0\u0026sid=ea134a4167a8e14cbe1835c5dab4aa9ab4dcgxrqa\u0026type=client\u0026tsoh=d3d3LnNjaWVuY2VkaXJlY3QuY29t\u0026ua=1113550654515750060a\u0026rr=7f6205eede60c185\u0026cc=kr)[FEAT: A general framework for Feature-aware Multivariate Time-series Representation Learning](https://pdf.sciencedirectassets.com/271505/1-s2.0-S0950705123X00161/1-s2.0-S0950705123005403/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEF8aCXVzLWVhc3QtMSJIMEYCIQD5hn8Mnl3gtFxq1nUFNfN4AkRGLGc0J7neyhwNqErOWgIhAPaV8bgoej7W9FIVIXRJEs1dJ4VCrxcjrjGRBp%2BkzRHlKrIFCBgQBRoMMDU5MDAzNTQ2ODY1IgyE6HLDOC7UTDUg0pkqjwUea8WEnsKUVN0tQyNMW2CZ0gIGG2DL4zI%2FOhz0UeagODZquX58pQLjvbMX9m5ohgzmh3UXgw6NklEoIDfnrs9%2BmRAiI0kOhB3SKGMmpYneL5TfxmSpLp51G53KC9usiYRZcxWti99qQVxTizvMEB8aaidOw7buJpMFN5%2FqZqNED0VGiTjIXh37Vs7kWfZ93M5ADP27q%2F4RwvixEekWumRgoOZr4JmpCAhgIAvdxT3A4Va%2BO4IHfqloPut4mBeFQflTBaF1VXEWGY2nKQNfvnjOvpk6jWIBrIkE4PCkDjPQVglUCVFbtkYn37DoEM6qz5o%2FJxDNT3fxyDMsJyzPqV4WJ6W22FoHjkXF4zUEOsJpwBiuAdwBQy5ej6%2BItgLt7p4Q%2BkhYpn%2F4Zdw8pn%2BPrhKVoI5%2B2NmePKc9xu9XSvh%2B%2F7oVotJArmAmeNiSl%2BNf4R848MQ%2Bilmg5MeeHbIFWJc2QGxFDOTWKJsds9yIgMfZIVMUzd2anx4MHvT6lW4qdFKXb9nxZj0%2BANXq2dyCMMUD4Bg5q6OzYJZsRkK3p6Bwh80m%2BAIDIzy6ze2KKpoLYs3eDniVHtZJJNL%2FjFUepIVM0QpaYF5bj1fODRi4MUGE%2B%2BR56LZ4LJdDZTqQV%2B1De9VNPmBJV7%2B8OHjSdI48agJ7kKg%2B30Cradn3xXPkiL6cXuRxuePwCcacJ8sNyVVEPJXK2W2tKYH8IuVm4GdAM1Q%2BmYMxpJzDsPE08FNN8AZ6n4ezHtoWHdxay6WzaiWpLOEKYaoDRHALfTuwsen3FtEqXFECsPYlPjDR6tH4Nndku4pfjw90CI7es4ggMqUoxzU8cbbojdDG%2FmOaeKztu7fQqDJGD9Z3mY9jJYxNs1HBMMLQ46YGOrABXQddNJuWvlRrRFyMKs%2FyWrIKde1VETUwdPd5o6xsXQOIqXtJaAt5zbDTfYMXJ9Mz0KiEkkE5Dayt33ozxrR9KKzYxKUtsd67zB3EWac8De%2FOX62MGAQCXlvYlVijjVPosfJXFvB7zD%2BKIppS7RUYYDpNqcW8DOQUDIOuSnk1VG3fVCDU88o81OBr2ZF%2Btt4mo8FyTK%2BgX0gmeMG%2BP1B1eZwglxj82329ZvmAEFv11ns%3D\u0026X-Amz-Algorithm=AWS4-HMAC-SHA256\u0026X-Amz-Date=20230813T153436Z\u0026X-Amz-SignedHeaders=host\u0026X-Amz-Expires=300\u0026X-Amz-Credential=ASIAQ3PHCVTYVHIZFQJK%2F20230813%2Fus-east-1%2Fs3%2Faws4_request\u0026X-Amz-Signature=edd52e1a7e3d9453d4620d4f1602656da03fadd4a82d3d5af1dc3e3ba8d45d32\u0026hash=c29b8e0b4587df019b2d07326b7a707d3765b18585be1a37c4047e8a4f6c5ebf\u0026host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61\u0026pii=S0950705123005403\u0026tid=spdf-df89dd41-6329-4760-8dc8-84cd1d0071f0\u0026sid=ea134a4167a8e14cbe1835c5dab4aa9ab4dcgxrqa\u0026type=client\u0026tsoh=d3d3LnNjaWVuY2VkaXJlY3QuY29t\u0026ua=1113550654515750060a\u0026rr=7f6205eede60c185\u0026cc=kr) | KBS |\n| 2023 | [](https://openreview.net/forum?id=OUWckW2g3j)[Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion](https://openreview.net/forum?id=OUWckW2g3j) | ICML |\n| 2023 | [](https://arxiv.org/abs/2303.01034)[Multi-Task Self-Supervised Time-Series Representation Learning](https://arxiv.org/abs/2303.01034) | arXiv |\n| 2023 | [](https://ieeexplore.ieee.org/document/10036065/)[Multivariate Time Series Representation Learning via Hierarchical Correlation Pooling Boosted Graph Neural Network](https://ieeexplore.ieee.org/document/10036065/) | IEEE TAI |\n| 2023 | [](https://proceedings.mlr.press/v202/ansari23a.html)[Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series](https://proceedings.mlr.press/v202/ansari23a.html) | ICML |\n| 2023 | [](https://openreview.net/forum?id=gMS6FVZvmF)[One Fits All: Power General Time Series Analysis by Pretrained LM](https://openreview.net/forum?id=gMS6FVZvmF) | NeurIPS |\n| 2023 | [](https://arxiv.org/abs/2302.06375)[One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data](https://arxiv.org/abs/2302.06375) | arXiv |\n| 2023 | [](https://arxiv.org/abs/2306.05880)[Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations](https://arxiv.org/abs/2306.05880) | arXiv |\n| 2023 | [](https://openreview.net/forum?id=ju_Uqw384Oq)[TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://openreview.net/forum?id=ju_Uqw384Oq) | ICLR |\n| 2023 | [](https://arxiv.org/abs/2303.13804)[UniTS: A Universal Time Series Analysis Framework with Self-supervised Representation Learning](https://arxiv.org/abs/2303.13804) | arXiv |\n| 2023 | [](https://dl.acm.org/doi/10.1145/3580305.3599549)[WHEN: A Wavelet-DTW Hybrid Attention Network for Heterogeneous Time Series Analysis](https://dl.acm.org/doi/10.1145/3580305.3599549) | KDD |\n| 2023 | [](https://dl.acm.org/doi/10.1145/3580305.3599508)[Sparse Binary Transformers for Multivariate Time Series Modeling](https://dl.acm.org/doi/10.1145/3580305.3599508) | KDD |\n| 2024 | [](https://arxiv.org/pdf/2306.06579)[Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder](https://arxiv.org/pdf/2306.06579) | ICDM |\n| 2024 | [](https://openreview.net/forum?id=bWcnvZ3qMb)[FITS: MODELING TIME SERIES WITH 10k PARAMETERS](https://openreview.net/forum?id=bWcnvZ3qMb) | ICLR |\n| 2024 | [](https://openreview.net/forum?id=QVVSb0GMXK)[NEWTIME: NUMERICALLY MULTI-SCALED EMBEDDING FOR LARGE-SCALE TIME SERIES PRETRAINING](https://openreview.net/forum?id=QVVSb0GMXK) | arXiv |\n| 2024 | [](https://openreview.net/forum?id=3y2TfP966N)[T-REP: REPRESENTATION LEARNING FOR TIME SERIES USING TIME-EMBEDDINGS](https://openreview.net/forum?id=3y2TfP966N) | ICLR |\n| 2024 | [](https://openreview.net/forum?id=4VIgNuQ1pY)[STABLE NEURAL STOCHASTIC DIFFERENTIAL EQUATIONS IN ANALYZING IRREGULAR TIME SERIES DATA](https://openreview.net/forum?id=4VIgNuQ1pY) | ICLR |\n| 2024 | [](https://openreview.net/pdf?id=O8ouVV8PjF)[CNN KERNELS CAN BE THE BEST SHAPELETS](https://openreview.net/pdf?id=O8ouVV8PjF) | ICLR |\n| 2024 | [](https://openreview.net/pdf?id=c56TWtYp0W)[GAFORMER: ENHANCING TIMESERIES TRANSFORMERS THROUGH GROUP-AWARE EMBEDDINGS](https://openreview.net/pdf?id=c56TWtYp0W) | ICLR |\n| 2024 | [](https://openreview.net/forum?id=MJksrOhurE)[CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting](https://openreview.net/forum?id=MJksrOhurE) | ICLR |\n| 2024 | [](https://arxiv.org/abs/2309.05305)[Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data](https://arxiv.org/abs/2309.05305) | AAAI |\n| 2024 | [](https://arxiv.org/abs/2403.00131)[UNITS: A Unified Multi-Task Time Series Model](https://arxiv.org/abs/2403.00131) | NeurIPS |\n| 2024 | [](https://openreview.net/forum?id=vpJMJerXHU)[MODERNTCN: A MODERN PURE CONVOLUTION STRUCTURE FOR GENERAL TIME SERIES ANALYSIS](https://openreview.net/forum?id=vpJMJerXHU) | ICLR |\n| 2024 | [](https://openreview.net/pdf?id=aR3uxWlZhX)[UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis](https://openreview.net/pdf?id=aR3uxWlZhX) | ICML |\n| 2024 | [](https://openreview.net/forum?id=CGR3vpX63X)[TSLANet: Rethinking Transformers for Time Series Representation Learning](https://openreview.net/forum?id=CGR3vpX63X) | ICML |\n| 2024 | [](https://openreview.net/forum?id=ecO7WOIlMD)[MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series](https://openreview.net/forum?id=ecO7WOIlMD) | ICML |\n| 2024 | [](https://openreview.net/forum?id=FVvf69a5rx)[MOMENT: A Family of Open Time-series Foundation Models](https://openreview.net/forum?id=FVvf69a5rx) | ICML |\n| 2024 | [](https://arxiv.org/abs/2405.10597)[UniCL: A Universal Contrastive Learning Framework for Large Time Series Models](https://arxiv.org/abs/2405.10597) | arXiv |\n| 2024 | [](https://arxiv.org/abs/2405.05959)[Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask](https://arxiv.org/abs/2405.05959) | KDD |\n| 2024 | [](https://openreview.net/forum?id=vMMzjCr5Zj\u0026noteId=DVwkuUpQiR)[Large Pre-trained time series models for cross-domain Time series analysis tasks](https://openreview.net/forum?id=vMMzjCr5Zj\u0026noteId=DVwkuUpQiR) | NeurIPS |\n| 2024 | [](https://openreview.net/forum?id=ncYGjx2vnE\u0026noteId=SB0dLuJeL7)[Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models](https://openreview.net/forum?id=ncYGjx2vnE\u0026noteId=SB0dLuJeL7) | NeurIPS |\n| 2024 | [](https://openreview.net/forum?id=5iUxMVJVEV\u0026noteId=fDQ5hBvom8)[Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis](https://openreview.net/forum?id=5iUxMVJVEV\u0026noteId=fDQ5hBvom8) | NeurIPS |\n| 2024 | [](https://openreview.net/forum?id=zm1LcgRpHm\u0026noteId=PQ6MFEkGOn)[Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representation](https://openreview.net/forum?id=zm1LcgRpHm\u0026noteId=PQ6MFEkGOn) | NeurIPS |\n| 2024 | [](https://openreview.net/pdf?id=tFB5SsabVb)[Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series](https://openreview.net/pdf?id=tFB5SsabVb) | NeurIPS |\n| 2024 | [](https://dl.acm.org/doi/pdf/10.1145/3627673.3679699)[Time-Series Representation Learning via Dual Reference Contrasting](https://dl.acm.org/doi/pdf/10.1145/3627673.3679699) | CIKM |\n| 2024 | [](https://openreview.net/pdf?id=GSnGPgeoS5)[iHyperTime: Interpretable Time Series Generation with Implicit Neural Representations](https://openreview.net/pdf?id=GSnGPgeoS5) | TMLR |\n| 2025 | [](https://arxiv.org/abs/2412.11376)[ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://arxiv.org/abs/2412.11376) | AAAI |\n| 2025 | [](https://arxiv.org/abs/2412.08906)[Federated Foundation Models on Heterogeneous Time Series](https://arxiv.org/abs/2412.08906) | AAAI |\n| 2025 | [](https://dl.acm.org/doi/10.1145/3696410.3714931)[Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals](https://dl.acm.org/doi/10.1145/3696410.3714931) | WWW |\n| 2025 | [](https://openreview.net/forum?id=1CLzLXSFNn)[TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis](https://openreview.net/forum?id=1CLzLXSFNn) | ICLR |\n| 2025 | [](https://openreview.net/forum?id=MZDdTzN6Cy)[TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation](https://openreview.net/forum?id=MZDdTzN6Cy) | ICLR |\n\n\n### Learning-Focused Approaches\n![examples of learning-focused approaches](https://github.com/user-attachments/assets/a1018c84-0ed2-4732-ab2a-583eb93b67f8)\n\n\u003e Studies in this category center on devising novel _learning objective_ functions for the representation learning process, i.e., model (pre-)training. As in the figure, these studies can be classified into three groups based on the learning objectives: task-adaptive, non-contrasting, and contrasting losses.\n\n| Year | Title | Venue |\n| ---- | ----- | ----- |\n| 2018 | [](https://proceedings.mlr.press/v84/wu18b.html)[Random Warping Series: A Random Features Method for Time-Series Embedding](https://proceedings.mlr.press/v84/wu18b.html) | AISTATS |\n| 2018 | [](https://link.springer.com/chapter/10.1007/978-3-030-10928-8_34)[Sqn2Vec: Learning Sequence Representation via Sequential Patterns with a Gap Constraint](https://link.springer.com/chapter/10.1007/978-3-030-10928-8_34) | ECML PKDD |\n| 2019 | [](https://ieeexplore.ieee.org/document/8736337)[Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representation](https://ieeexplore.ieee.org/document/8736337) | IEEE/ACM TASLP |\n| 2019 | [](https://link.springer.com/chapter/10.1007/978-3-030-46133-1_19)[Learning Disentangled Representations of Satellite Image Time Series](https://link.springer.com/chapter/10.1007/978-3-030-46133-1_19) | ECML PKDD |\n| 2019 | [](https://proceedings.neurips.cc/paper_files/paper/2019/hash/53c6de78244e9f528eb3e1cda69699bb-Abstract.html)[Unsupervised Scalable Representation Learning for Multivariate Time Series](https://proceedings.neurips.cc/paper_files/paper/2019/hash/53c6de78244e9f528eb3e1cda69699bb-Abstract.html) | NeurIPS |\n| 2019 | [](https://www.sciencedirect.com/science/article/pii/S092523121830626X)[Wave2Vec: Deep representation learning for clinical temporal data](https://www.sciencedirect.com/science/article/pii/S092523121830626X) | Neurocomputing |\n| 2020 | [](https://proceedings.neurips.cc/paper/2020/hash/5c9452254bccd24b8ad0bb1ab4408ad1-Abstract.html)[Cycle-Contrast for Self-Supervised Video Representation Learning](https://proceedings.neurips.cc/paper/2020/hash/5c9452254bccd24b8ad0bb1ab4408ad1-Abstract.html) | NeurIPS |\n| 2020 | [](https://ieeexplore.ieee.org/document/8685795)[End-to-End Incomplete Time-Series Modeling From Linear Memory of Latent Variables](https://ieeexplore.ieee.org/document/8685795) | IEEE TCYB |\n| 2020 | [](https://proceedings.neurips.cc/paper/2020/hash/328e5d4c166bb340b314d457a208dc83-Abstract.html)[Learning Representations from Audio-Visual Spatial Alignment](https://proceedings.neurips.cc/paper/2020/hash/328e5d4c166bb340b314d457a208dc83-Abstract.html) | NeurIPS |\n| 2020 | [](https://link.springer.com/chapter/10.1007/978-3-030-58580-8_19)[Memory-Augmented Dense Predictive Coding for Video Representation Learning](https://link.springer.com/chapter/10.1007/978-3-030-58580-8_19) | ECCV |\n| 2020 | [](https://link.springer.com/chapter/10.1007/978-3-030-58520-4_30)[Self-supervised Video Representation Learning by Pace Prediction](https://link.springer.com/chapter/10.1007/978-3-030-58520-4_30) | ECCV |\n| 2020 | [](https://arxiv.org/abs/2010.01596)[TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series](https://arxiv.org/abs/2010.01596) | arXiv |\n| 2021 | [](https://dl.acm.org/doi/10.1145/3447548.3467401)[A Transformer-based Framework for Multivariate Time Series Representation Learning](https://dl.acm.org/doi/10.1145/3447548.3467401) | KDD |\n| 2021 | [](https://openaccess.thecvf.com/content/CVPR2021/html/Haresh_Learning_by_Aligning_Videos_in_Time_CVPR_2021_paper.html)[Learning by aligning videos in time](https://openaccess.thecvf.com/content/CVPR2021/html/Haresh_Learning_by_Aligning_Videos_in_Time_CVPR_2021_paper.html) | CVPR |\n| 2021 | [](https://openaccess.thecvf.com/content/ICCV2021/html/Behrmann_Long_Short_View_Feature_Decomposition_via_Contrastive_Video_Representation_Learning_ICCV_2021_paper.html)[Long Short View Feature Decomposition via Contrastive Video Representation Learning](https://openaccess.thecvf.com/content/ICCV2021/html/Behrmann_Long_Short_View_Feature_Decomposition_via_Contrastive_Video_Representation_Learning_ICCV_2021_paper.html) | ICCV |\n| 2021 | [](https://openaccess.thecvf.com/content/CVPR2021/html/Hadji_Representation_Learning_via_Global_Temporal_Alignment_and_Cycle-Consistency_CVPR_2021_paper.html)[Representation Learning via Global Temporal Alignment and Cycle-Consistency](https://openaccess.thecvf.com/content/CVPR2021/html/Hadji_Representation_Learning_via_Global_Temporal_Alignment_and_Cycle-Consistency_CVPR_2021_paper.html) | CVPR |\n| 2021 | [](https://ojs.aaai.org/index.php/AAAI/article/view/16189)[RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning](https://ojs.aaai.org/index.php/AAAI/article/view/16189) | AAAI |\n| 2021 | [](https://openaccess.thecvf.com/content/CVPR2021/html/Qian_Spatiotemporal_Contrastive_Video_Representation_Learning_CVPR_2021_paper.html)[Spatiotemporal Contrastive Video Representation Learning](https://openaccess.thecvf.com/content/CVPR2021/html/Qian_Spatiotemporal_Contrastive_Video_Representation_Learning_CVPR_2021_paper.html) | CVPR |\n| 2021 | [](https://openaccess.thecvf.com/content/ICCV2021/html/Jenni_Time-Equivariant_Contrastive_Video_Representation_Learning_ICCV_2021_paper.html)[Time-Equivariant Contrastive Video Representation Learning](https://openaccess.thecvf.com/content/ICCV2021/html/Jenni_Time-Equivariant_Contrastive_Video_Representation_Learning_ICCV_2021_paper.html) | ICCV |\n| 2021 | [](https://www.ijcai.org/proceedings/2021/324)[Time-Series Representation Learning via Temporal and Contextual Contrasting](https://www.ijcai.org/proceedings/2021/324) | IJCAI |\n| 2021 | [](https://proceedings.neurips.cc/paper_files/paper/2021/hash/51200d29d1fc15f5a71c1dab4bb54f7c-Abstract.html)[TriBERT: Human-centric Audio-visual Representation Learning](https://proceedings.neurips.cc/paper_files/paper/2021/hash/51200d29d1fc15f5a71c1dab4bb54f7c-Abstract.html) | NeurIPS |\n| 2021 | [](https://openreview.net/forum?id=8qDwejCuCN)[Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://openreview.net/forum?id=8qDwejCuCN) | ICLR |\n| 2022 | [](https://ojs.aaai.org/index.php/AAAI/article/view/20248)[Contrastive Spatio-Temporal Pretext Learning for Self-Supervised Video Representation](https://ojs.aaai.org/index.php/AAAI/article/view/20248) | AAAI |\n| 2022 | [](https://openaccess.thecvf.com/content/CVPR2022/html/Guo_Cross-Architecture_Self-Supervised_Video_Representation_Learning_CVPR_2022_paper.html)[Cross-Architecture Self-supervised Video Representation Learning](https://openaccess.thecvf.com/content/CVPR2022/html/Guo_Cross-Architecture_Self-Supervised_Video_Representation_Learning_CVPR_2022_paper.html) | CVPR |\n| 2022 | [](https://dl.acm.org/doi/abs/10.1145/3503161.3547783)[Dual Contrastive Learning for Spatio-temporal Representation](https://dl.acm.org/doi/abs/10.1145/3503161.3547783) | MM |\n| 2022 | [](https://openaccess.thecvf.com/content/CVPR2022/html/Chen_Frame-Wise_Action_Representations_for_Long_Videos_via_Sequence_Contrastive_Learning_CVPR_2022_paper.html)[Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning](https://openaccess.thecvf.com/content/CVPR2022/html/Chen_Frame-Wise_Action_Representations_for_Long_Videos_via_Sequence_Contrastive_Learning_CVPR_2022_paper.html) | CVPR |\n| 2022 | [](https://openaccess.thecvf.com/content/WACV2022/html/Zhang_Hierarchically_Decoupled_Spatial-Temporal_Contrast_for_Self-Supervised_Video_Representation_Learning_WACV_2022_paper.html)[Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning](https://openaccess.thecvf.com/content/WACV2022/html/Zhang_Hierarchically_Decoupled_Spatial-Temporal_Contrast_for_Self-Supervised_Video_Representation_Learning_WACV_2022_paper.html) | WACV |\n| 2022 | [](https://openaccess.thecvf.com/content/CVPR2022/html/Qing_Learning_From_Untrimmed_Videos_Self-Supervised_Video_Representation_Learning_With_Hierarchical_CVPR_2022_paper.html)[Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency](https://openaccess.thecvf.com/content/CVPR2022/html/Qing_Learning_From_Untrimmed_Videos_Self-Supervised_Video_Representation_Learning_With_Hierarchical_CVPR_2022_paper.html) | CVPR |\n| 2022 | [](https://bmvc2022.mpi-inf.mpg.de/0541.pdf)[On Temporal Granularity in Self-Supervised Video Representation Learning](https://bmvc2022.mpi-inf.mpg.de/0541.pdf) | BMVC |\n| 2022 | [](https://openreview.net/forum?id=OJ4mMfGKLN)[Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://openreview.net/forum?id=OJ4mMfGKLN) | NeurIPS |\n| 2022 | [](https://ojs.aaai.org/index.php/AAAI/article/view/20047)[Self-Supervised Spatiotemporal Representation Learning by Exploiting Video Continuity](https://ojs.aaai.org/index.php/AAAI/article/view/20047) | AAAI |\n| 2022 | [](https://openreview.net/forum?id=nhtkdCvVLIh)[Self-Supervised Time Series Representation Learning with Temporal-Instance Similarity Distillation](https://openreview.net/forum?id=nhtkdCvVLIh) | ICML (Workshop) |\n| 2022 | [](https://ieeexplore.ieee.org/abstract/document/9352025)[Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics](https://ieeexplore.ieee.org/abstract/document/9352025) | IEEE TPAMI |\n| 2022 | [](https://dl.acm.org/doi/10.1145/3534678.3539329)[TARNet: Task-Aware Reconstruction for Time-Series Transformer](https://dl.acm.org/doi/10.1145/3534678.3539329) | KDD |\n| 2022 | [](https://ieeexplore.ieee.org/abstract/document/9713748)[TCGL: Temporal Contrastive Graph for Self-Supervised Video Representation Learning](https://ieeexplore.ieee.org/abstract/document/9713748) | IEEE TIP |\n| 2022 | [](https://www.sciencedirect.com/science/article/pii/S1077314222000376)[TCLR: Temporal contrastive learning for video representation](https://www.sciencedirect.com/science/article/pii/S1077314222000376) | CVIU |\n| 2022 | [](https://www.sciencedirect.com/science/article/abs/pii/S0950705122002726)[TimeCLR: A self-supervised contrastive learning framework for univariate time series representation](https://www.sciencedirect.com/science/article/abs/pii/S0950705122002726) | KBS |\n| 2022 | [](https://openaccess.thecvf.com/content/CVPR2022/html/Duan_TransRank_Self-Supervised_Video_Representation_Learning_via_Ranking-Based_Transformation_Recognition_CVPR_2022_paper.html)[TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition](https://openaccess.thecvf.com/content/CVPR2022/html/Duan_TransRank_Self-Supervised_Video_Representation_Learning_via_Ranking-Based_Transformation_Recognition_CVPR_2022_paper.html) | CVPR |\n| 2022 | [](https://sslneurips22.github.io/paper_pdfs/paper_74.pdf)[TS-Rep: Self-supervised time series representation learning from robot sensor data](https://sslneurips22.github.io/paper_pdfs/paper_74.pdf) | NeurIPS (Workshop) |\n| 2022 | [](https://ojs.aaai.org/index.php/AAAI/article/view/20881)[TS2Vec: Towards Universal Representation of Time Series](https://ojs.aaai.org/index.php/AAAI/article/view/20881) | AAAI |\n| 2022 | [](https://ieeexplore.ieee.org/document/9878692/)[Weakly Paired Associative Learning for Sound and Image Representations via Bimodal Associative Memory](https://ieeexplore.ieee.org/document/9878692/) | CVPR |\n| 2023 | [](https://www.vldb.org/pvldb/vol17/p386-wang.pdf)[A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning](https://www.vldb.org/pvldb/vol17/p386-wang.pdf) | VLDB |\n| 2023 | [](https://openreview.net/forum?id=sOQBHlCmzp)[Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series](https://openreview.net/forum?id=sOQBHlCmzp) | NeurIPS |\n| 2023 | [](https://dl.acm.org/doi/10.1145/3583780.3614759)[A Co-training Approach for Noisy Time Series Learning](https://dl.acm.org/doi/10.1145/3583780.3614759) | CIKM |\n| 2023 | [](https://ojs.aaai.org/index.php/AAAI/article/view/25915)[Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling](https://ojs.aaai.org/index.php/AAAI/article/view/25915) | AAAI |\n| 2023 | [](https://arxiv.org/abs/2310.11959)[A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis](https://arxiv.org/abs/2310.11959) | VLDB |\n| 2023 | [](https://openreview.net/forum?id=l4CZCKXoSn)[FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space](https://openreview.net/forum?id=l4CZCKXoSn) | NeurIPS |\n| 2023 | [](https://pdf.sciencedirectassets.com/271505/1-s2.0-S0950705123X00161/1-s2.0-S0950705123005403/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEF8aCXVzLWVhc3QtMSJIMEYCIQD5hn8Mnl3gtFxq1nUFNfN4AkRGLGc0J7neyhwNqErOWgIhAPaV8bgoej7W9FIVIXRJEs1dJ4VCrxcjrjGRBp%2BkzRHlKrIFCBgQBRoMMDU5MDAzNTQ2ODY1IgyE6HLDOC7UTDUg0pkqjwUea8WEnsKUVN0tQyNMW2CZ0gIGG2DL4zI%2FOhz0UeagODZquX58pQLjvbMX9m5ohgzmh3UXgw6NklEoIDfnrs9%2BmRAiI0kOhB3SKGMmpYneL5TfxmSpLp51G53KC9usiYRZcxWti99qQVxTizvMEB8aaidOw7buJpMFN5%2FqZqNED0VGiTjIXh37Vs7kWfZ93M5ADP27q%2F4RwvixEekWumRgoOZr4JmpCAhgIAvdxT3A4Va%2BO4IHfqloPut4mBeFQflTBaF1VXEWGY2nKQNfvnjOvpk6jWIBrIkE4PCkDjPQVglUCVFbtkYn37DoEM6qz5o%2FJxDNT3fxyDMsJyzPqV4WJ6W22FoHjkXF4zUEOsJpwBiuAdwBQy5ej6%2BItgLt7p4Q%2BkhYpn%2F4Zdw8pn%2BPrhKVoI5%2B2NmePKc9xu9XSvh%2B%2F7oVotJArmAmeNiSl%2BNf4R848MQ%2Bilmg5MeeHbIFWJc2QGxFDOTWKJsds9yIgMfZIVMUzd2anx4MHvT6lW4qdFKXb9nxZj0%2BANXq2dyCMMUD4Bg5q6OzYJZsRkK3p6Bwh80m%2BAIDIzy6ze2KKpoLYs3eDniVHtZJJNL%2FjFUepIVM0QpaYF5bj1fODRi4MUGE%2B%2BR56LZ4LJdDZTqQV%2B1De9VNPmBJV7%2B8OHjSdI48agJ7kKg%2B30Cradn3xXPkiL6cXuRxuePwCcacJ8sNyVVEPJXK2W2tKYH8IuVm4GdAM1Q%2BmYMxpJzDsPE08FNN8AZ6n4ezHtoWHdxay6WzaiWpLOEKYaoDRHALfTuwsen3FtEqXFECsPYlPjDR6tH4Nndku4pfjw90CI7es4ggMqUoxzU8cbbojdDG%2FmOaeKztu7fQqDJGD9Z3mY9jJYxNs1HBMMLQ46YGOrABXQddNJuWvlRrRFyMKs%2FyWrIKde1VETUwdPd5o6xsXQOIqXtJaAt5zbDTfYMXJ9Mz0KiEkkE5Dayt33ozxrR9KKzYxKUtsd67zB3EWac8De%2FOX62MGAQCXlvYlVijjVPosfJXFvB7zD%2BKIppS7RUYYDpNqcW8DOQUDIOuSnk1VG3fVCDU88o81OBr2ZF%2Btt4mo8FyTK%2BgX0gmeMG%2BP1B1eZwglxj82329ZvmAEFv11ns%3D\u0026X-Amz-Algorithm=AWS4-HMAC-SHA256\u0026X-Amz-Date=20230813T153436Z\u0026X-Amz-SignedHeaders=host\u0026X-Amz-Expires=300\u0026X-Amz-Credential=ASIAQ3PHCVTYVHIZFQJK%2F20230813%2Fus-east-1%2Fs3%2Faws4_request\u0026X-Amz-Signature=edd52e1a7e3d9453d4620d4f1602656da03fadd4a82d3d5af1dc3e3ba8d45d32\u0026hash=c29b8e0b4587df019b2d07326b7a707d3765b18585be1a37c4047e8a4f6c5ebf\u0026host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61\u0026pii=S0950705123005403\u0026tid=spdf-df89dd41-6329-4760-8dc8-84cd1d0071f0\u0026sid=ea134a4167a8e14cbe1835c5dab4aa9ab4dcgxrqa\u0026type=client\u0026tsoh=d3d3LnNjaWVuY2VkaXJlY3QuY29t\u0026ua=1113550654515750060a\u0026rr=7f6205eede60c185\u0026cc=kr)[FEAT: A general framework for Feature-aware Multivariate Time-series Representation Learning](https://pdf.sciencedirectassets.com/271505/1-s2.0-S0950705123X00161/1-s2.0-S0950705123005403/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEF8aCXVzLWVhc3QtMSJIMEYCIQD5hn8Mnl3gtFxq1nUFNfN4AkRGLGc0J7neyhwNqErOWgIhAPaV8bgoej7W9FIVIXRJEs1dJ4VCrxcjrjGRBp%2BkzRHlKrIFCBgQBRoMMDU5MDAzNTQ2ODY1IgyE6HLDOC7UTDUg0pkqjwUea8WEnsKUVN0tQyNMW2CZ0gIGG2DL4zI%2FOhz0UeagODZquX58pQLjvbMX9m5ohgzmh3UXgw6NklEoIDfnrs9%2BmRAiI0kOhB3SKGMmpYneL5TfxmSpLp51G53KC9usiYRZcxWti99qQVxTizvMEB8aaidOw7buJpMFN5%2FqZqNED0VGiTjIXh37Vs7kWfZ93M5ADP27q%2F4RwvixEekWumRgoOZr4JmpCAhgIAvdxT3A4Va%2BO4IHfqloPut4mBeFQflTBaF1VXEWGY2nKQNfvnjOvpk6jWIBrIkE4PCkDjPQVglUCVFbtkYn37DoEM6qz5o%2FJxDNT3fxyDMsJyzPqV4WJ6W22FoHjkXF4zUEOsJpwBiuAdwBQy5ej6%2BItgLt7p4Q%2BkhYpn%2F4Zdw8pn%2BPrhKVoI5%2B2NmePKc9xu9XSvh%2B%2F7oVotJArmAmeNiSl%2BNf4R848MQ%2Bilmg5MeeHbIFWJc2QGxFDOTWKJsds9yIgMfZIVMUzd2anx4MHvT6lW4qdFKXb9nxZj0%2BANXq2dyCMMUD4Bg5q6OzYJZsRkK3p6Bwh80m%2BAIDIzy6ze2KKpoLYs3eDniVHtZJJNL%2FjFUepIVM0QpaYF5bj1fODRi4MUGE%2B%2BR56LZ4LJdDZTqQV%2B1De9VNPmBJV7%2B8OHjSdI48agJ7kKg%2B30Cradn3xXPkiL6cXuRxuePwCcacJ8sNyVVEPJXK2W2tKYH8IuVm4GdAM1Q%2BmYMxpJzDsPE08FNN8AZ6n4ezHtoWHdxay6WzaiWpLOEKYaoDRHALfTuwsen3FtEqXFECsPYlPjDR6tH4Nndku4pfjw90CI7es4ggMqUoxzU8cbbojdDG%2FmOaeKztu7fQqDJGD9Z3mY9jJYxNs1HBMMLQ46YGOrABXQddNJuWvlRrRFyMKs%2FyWrIKde1VETUwdPd5o6xsXQOIqXtJaAt5zbDTfYMXJ9Mz0KiEkkE5Dayt33ozxrR9KKzYxKUtsd67zB3EWac8De%2FOX62MGAQCXlvYlVijjVPosfJXFvB7zD%2BKIppS7RUYYDpNqcW8DOQUDIOuSnk1VG3fVCDU88o81OBr2ZF%2Btt4mo8FyTK%2BgX0gmeMG%2BP1B1eZwglxj82329ZvmAEFv11ns%3D\u0026X-Amz-Algorithm=AWS4-HMAC-SHA256\u0026X-Amz-Date=20230813T153436Z\u0026X-Amz-SignedHeaders=host\u0026X-Amz-Expires=300\u0026X-Amz-Credential=ASIAQ3PHCVTYVHIZFQJK%2F20230813%2Fus-east-1%2Fs3%2Faws4_request\u0026X-Amz-Signature=edd52e1a7e3d9453d4620d4f1602656da03fadd4a82d3d5af1dc3e3ba8d45d32\u0026hash=c29b8e0b4587df019b2d07326b7a707d3765b18585be1a37c4047e8a4f6c5ebf\u0026host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61\u0026pii=S0950705123005403\u0026tid=spdf-df89dd41-6329-4760-8dc8-84cd1d0071f0\u0026sid=ea134a4167a8e14cbe1835c5dab4aa9ab4dcgxrqa\u0026type=client\u0026tsoh=d3d3LnNjaWVuY2VkaXJlY3QuY29t\u0026ua=1113550654515750060a\u0026rr=7f6205eede60c185\u0026cc=kr) | KBS |\n| 2023 | [](https://openaccess.thecvf.com/content/CVPR2023/html/Zhang_Modeling_Video_As_Stochastic_Processes_for_Fine-Grained_Video_Representation_Learning_CVPR_2023_paper.html)[Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning](https://openaccess.thecvf.com/content/CVPR2023/html/Zhang_Modeling_Video_As_Stochastic_Processes_for_Fine-Grained_Video_Representation_Learning_CVPR_2023_paper.html) | CVPR |\n| 2023 | [](https://arxiv.org/abs/2303.01034)[Multi-Task Self-Supervised Time-Series Representation Learning](https://arxiv.org/abs/2303.01034) | arXiv |\n| 2023 | [](https://ojs.aaai.org/index.php/AAAI/article/view/25876)[PrimeNet: Pre-Training for Irregular Multivariate Time Series](https://ojs.aaai.org/index.php/AAAI/article/view/25876) | AAAI |\n| 2023 | [](https://openreview.net/forum?id=ginTcBUnL8)[SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling](https://openreview.net/forum?id=ginTcBUnL8) | NeurIPS |\n| 2023 | [](https://openreview.net/forum?id=CIFOsnhZvON)[TempCLR: Temporal Alignment Representation with Contrastive Learning](https://openreview.net/forum?id=CIFOsnhZvON) | ICLR |\n| 2023 | [](https://arxiv.org/abs/2301.08871)[Ti-MAE: Self-Supervised Masked Time Series Autoencoders](https://arxiv.org/abs/2301.08871) | arXiv |\n| 2023 | [](https://openreview.net/pdf?id=EvGOdASdHi)[Context Consistency Regularization for Label Sparsity in Time Series](https://openreview.net/pdf?id=EvGOdASdHi) | ICML |\n| 2024 | [](https://arxiv.org/pdf/2306.06579)[Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder](https://arxiv.org/pdf/2306.06579) | ICDM |\n| 2024 | [](https://openreview.net/forum?id=3y2TfP966N)[T-REP: REPRESENTATION LEARNING FOR TIME SERIES USING TIME-EMBEDDINGS](https://openreview.net/forum?id=3y2TfP966N) | ICLR |\n| 2024 | [](https://openreview.net/forum?id=Tuh4nZVb0g)[TEST: TEXT PROTOTYPE ALIGNED EMBEDDING TO ACTIVATE LLM’S ABILITY FOR TIME SERIES](https://openreview.net/forum?id=Tuh4nZVb0g) | ICLR |\n| 2024 | [](https://arxiv.org/abs/2312.15709)[TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://arxiv.org/abs/2312.15709) | AAAI |\n| 2024 | [](https://www.sciencedirect.com/science/article/pii/S0031320323006416)[Multi-scale self-supervised representation learning with temporal alignment for multi-rate time series modeling](https://www.sciencedirect.com/science/article/pii/S0031320323006416) | Pattern Recognition |\n| 2024 | [](https://openreview.net/forum?id=pAsQSWlDUf)[SOFT CONTRASTIVE LEARNING FOR TIME SERIES](https://openreview.net/forum?id=pAsQSWlDUf) | ICLR |\n| 2024 | [](https://openreview.net/forum?id=WS7GuBDFa2)[LEARNING TO EMBED TIME SERIES PATCHES INDEPENDENTLY](https://openreview.net/forum?id=WS7GuBDFa2) | ICLR |\n| 2024 | [](https://openreview.net/forum?id=3zQo5oUvia)[RETRIEVAL-BASED RECONSTRUCTION FOR TIME-SERIES CONTRASTIVE LEARNING](https://openreview.net/forum?id=3zQo5oUvia) | ICLR |\n| 2024 | [](https://openreview.net/forum?id=MJksrOhurE)[CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting](https://openreview.net/forum?id=MJksrOhurE) | ICLR |\n| 2024 | [](https://arxiv.org/abs/2309.05305)[Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data](https://arxiv.org/abs/2309.05305) | AAAI |\n| 2024 | [](https://arxiv.org/abs/2403.00131)[UNITS: A Unified Multi-Task Time Series Model](https://arxiv.org/abs/2403.00131) | NeurIPS |\n| 2024 | [](https://openreview.net/pdf?id=aR3uxWlZhX)[UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis](https://openreview.net/pdf?id=aR3uxWlZhX) | ICML |\n| 2024 | [](https://openreview.net/forum?id=bYRYb7DMNo)[Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://openreview.net/forum?id=bYRYb7DMNo) | ICML |\n| 2024 | [](https://openreview.net/forum?id=Rx9GMufByc)[Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning](https://openreview.net/forum?id=Rx9GMufByc) | ICML |\n| 2024 | [](https://openreview.net/forum?id=ecO7WOIlMD)[MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series](https://openreview.net/forum?id=ecO7WOIlMD) | ICML |\n| 2024 | [](https://openreview.net/forum?id=wrTzLoqbCg)[TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling](https://openreview.net/forum?id=wrTzLoqbCg) | ICML |\n| 2024 | [](https://arxiv.org/abs/2405.10597)[UniCL: A Universal Contrastive Learning Framework for Large Time Series Models](https://arxiv.org/abs/2405.10597) | arXiv |\n| 2024 | [](https://arxiv.org/abs/2405.05959)[Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask](https://arxiv.org/abs/2405.05959) | KDD |\n| 2024 | [](https://openreview.net/forum?id=vMMzjCr5Zj\u0026noteId=DVwkuUpQiR)[Large Pre-trained time series models for cross-domain Time series analysis tasks](https://openreview.net/forum?id=vMMzjCr5Zj\u0026noteId=DVwkuUpQiR) | NeurIPS |\n| 2024 | [](https://dl.acm.org/doi/pdf/10.1145/3627673.3679699)[Time-Series Representation Learning via Dual Reference Contrasting](https://dl.acm.org/doi/pdf/10.1145/3627673.3679699) | CIKM |\n| 2025 | [](https://arxiv.org/abs/2412.11376)[ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://arxiv.org/abs/2412.11376) | AAAI |\n| 2025 | [](https://arxiv.org/abs/2412.08906)[Federated Foundation Models on Heterogeneous Time Series](https://arxiv.org/abs/2412.08906) | AAAI |\n| 2025 | [](https://arxiv.org/abs/2412.20790)[Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning](https://arxiv.org/abs/2412.20790) | AAAI |\n| 2025 | [](https://arxiv.org/abs/2412.12886)[TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis](https://arxiv.org/abs/2412.12886) | AAAI |\n| 2025 | [](https://arxiv.org/abs/2401.04979)[DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis](https://arxiv.org/abs/2401.04979) | AAAI |\n| 2025 | [](https://dl.acm.org/doi/10.1145/3696410.3714931)[Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals](https://dl.acm.org/doi/10.1145/3696410.3714931) | WWW |\n| 2025 | [](https://openreview.net/forum?id=8zJRon6k5v)[Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series](https://openreview.net/forum?id=8zJRon6k5v) | ICLR |\n\n\n\n## Relevant Studies on Open Challenges\n\n### Time-Series Active Learning\n\n| **Title** | **Affiliation** | **Venue** | **Year** |\n| --- | --- | --- | --- |\n| [Coherence-based Label Propagation over Time Series for Accelerated Active Learning](https://openreview.net/forum?id=gjNcH0hj0LM) | KAIST | ICLR | 2021 |\n| [Are all frames equal? active sparse labeling for video action detection](https://dl.acm.org/doi/10.5555/3600270.3601314) | University of Central Florida | NeurIPS | 2022 |\n| [Active Learning Framework for Time-Series Classification of Vibration and Industrial Process Data](https://papers.phmsociety.org/index.php/phmconf/article/view/3059) | Viking Analytics | Annual Conference of the PHM Society | 2021 |\n| [Active learning for sampling in time-series experiments with application to gene expression analysis](https://dl.acm.org/doi/10.1145/1102351.1102456) | MIT | ICML | 2005 |\n\n### Distribution Shifts and Adaptation\n\n| **Title** | **Affiliation** | **Venue** | **Year** |\n| --- | --- | --- | --- |\n| [Concept Drift Detection in Data Stream Mining : A literature review](https://www.sciencedirect.com/science/article/pii/S1319157821003062) | Motilal Nehru National Institute of Technology Allahabad | Journal of King Saud University - Computer and Information Sciences | 2022|\n| [Recent Advances in Concept Drift Adaptation Methods for Deep Learning](https://www.ijcai.org/proceedings/2022/788) | Huazhong University of Science and Technology | IJCAI | 2022 |\n| [ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data](https://dl.acm.org/doi/10.1145/3587937) | Institute for Infocomm Research and Centre for Frontier AI Research | ACM TKDD | 2023 |\n| [Domain Adaptation for Time Series Forecasting via Attention Sharing](https://arxiv.org/abs/2102.06828) | University of California Santa Barbara, California | ICML | 2022 |\n| [Contrastive Learning for Unsupervised Domain Adaptation of Time Series](https://arxiv.org/abs/2206.06243) | ETH Zürich | ICLR | 2023 |\n| [Out-of-Distribution Generalization in Time Series: A Survey](https://www.sciencedirect.com/science/article/abs/pii/S1566253526002150) | Southwest Jiaotong University | Information Fusion | 2026 |\n\n\n### Reliable Data Augmentation\n\n| **Title** | **Affiliation** | **Venue** | **Year** |\n| --- | --- | --- | --- |\n| [Time series contrastive learning with information-aware augmentations](https://dl.acm.org/doi/10.1609/aaai.v37i4.25575) | Florida International University | AAAI | 2023 |\n| [Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning](https://openreview.net/forum?id=dbVRDk2wt7) | ETH Zurich | NeurIPS | 2023 |\n\n\n### Neural Architecture Search (NAS)\n\n| **Title** | **Affiliation** | **Venue** | **Year** |\n| --- | --- | --- | --- |\n| [Neural Architecture Search: Insights from 1000 Papers](https://arxiv.org/abs/2301.08727) | Abacus.AI | arXiv | 2023 |\n| [LightCTS: A Lightweight Framework for Correlated Time Series Forecasting](https://dl.acm.org/doi/10.1145/3589270) | Aalborg University | PACMMOD | 2023 |\n| [AutoTransformer: Automatic Transformer Architecture Design for Time Series Classification](https://dl.acm.org/doi/10.1007/978-3-031-05933-9_12) | Ant Group | PAKDD | 2022 | \n| [PASTA: Neural Architecture Search for Anomaly Detection in Multivariate Time Series](https://ieeexplore.ieee.org/document/10787122) | KAIST | IEEE TETCI | 2024 |\n| [TFAS: zero-shot NAS for general time-series analysis with time-frequency aware scoring](https://link.springer.com/article/10.1007/s10994-025-06832-y) | DeepAuto.ai | Machine Learning | 2025 |\n\n### Multi-Modal Representation Learning\n\n| **Title** | **Affiliation** | **Venue** | **Year** |\n| --- | --- | --- | --- |\n| [Learning Transferable Visual Models From Natural Language Supervision](https://proceedings.mlr.press/v139/radford21a) | OpenAI | ICML | 2021 |\n| [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://proceedings.mlr.press/v139/jia21b.html) | Google Research | ICML | 2021 |\n\n### Interpretability, Fairness, and Responsible Use\n\n| **Title** | **Affiliation** | **Venue** | **Year** |\n| --- | --- | --- | --- |\n| [Interpretable time series neural representation for classification purposes](https://ieeexplore.ieee.org/document/10302534) | Sorbonne Université | IEEE DSAA | 2023 |\n| [Time series representations classroom (TSRC): a teacher-student-based framework for interpretability-enhanced unsupervised time series representation learning](https://link.springer.com/article/10.1007/s10994-025-06895-x) | RWTH Aachen University | Machine Learning | 2025 |\n\n\n\n## Neighbor Repositories\n- https://github.com/qingsongedu/awesome-AI-for-time-series-papers\n- https://github.com/qianlima-lab/time-series-ptms\n- https://github.com/qingsongedu/time-series-transformers-review\t\t\t\t\n- https://github.com/lixus7/Time-Series-Works-Conferences\t\t\t\t\n- https://github.com/qingsongedu/Awesome-TimeSeries-AIOps-LM-LLM\n- https://github.com/qingsongedu/Awesome-SSL4TS\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/itouchz%2Fawesome-deep-time-series-representations/projects"}