https://github.com/ddz16/tsfpaper
This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.
https://github.com/ddz16/tsfpaper
deep-learning deep-neural-networks paper-lists rnn spatial-temporal-forecasting spatio-temporal spatio-temporal-data spatio-temporal-prediction tcn time-series time-series-analysis time-series-forecasting time-series-models time-series-prediction transformer
Last synced: 5 months ago
JSON representation
This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.
- Host: GitHub
- URL: https://github.com/ddz16/tsfpaper
- Owner: ddz16
- Created: 2022-06-29T09:44:56.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2024-04-09T12:10:18.000Z (about 2 years ago)
- Last Synced: 2024-04-09T16:25:11.691Z (about 2 years ago)
- Topics: deep-learning, deep-neural-networks, paper-lists, rnn, spatial-temporal-forecasting, spatio-temporal, spatio-temporal-data, spatio-temporal-prediction, tcn, time-series, time-series-analysis, time-series-forecasting, time-series-models, time-series-prediction, transformer
- Homepage:
- Size: 769 KB
- Stars: 1,313
- Watchers: 55
- Forks: 119
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Awesome Time Series Forecasting/Prediction Papers
[](https://awesome.re)
This repository contains a reading list of papers (**400+ papers !!!**) on **Time Series Forecasting/Prediction (TSF)** and **Spatio-Temporal Forecasting/Prediction (STF)**. These papers are mainly categorized according to the type of model. **This repository is still being continuously improved. In addition to papers that have been accepted by top conferences or journals, the repository also includes the latest papers from [arXiv](https://arxiv.org/). If you have found any relevant papers that need to be included in this repository, please feel free to submit a pull request (PR) or open an issue.** If you find this repository useful, please give it a 🌟.
Each paper may apply to one or several types of forecasting, including univariate time series forecasting, multivariate time series forecasting, and spatio-temporal forecasting, which are also marked in the Type column. **If covariates and exogenous variables are not considered**, univariate time series forecasting involves predicting the future of one variable with the history of this variable, while multivariate time series forecasting involves predicting the future of C variables with the history of C variables. **Note that repeating univariate forecasting multiple times can also achieve the goal of multivariate forecasting, which is called _channel-independent_. However, univariate forecasting methods cannot extract relationships between variables, so the basis for distinguishing between univariate and multivariate forecasting methods is whether the method involves interaction between variables. Besides, in the era of deep learning, many univariate models can be easily modified to directly process multiple variables for multivariate forecasting. And multivariate models generally can be directly used for univariate forecasting. Here we classify solely based on the model's description in the original paper.** Spatio-temporal forecasting is often used in traffic and weather forecasting, and it adds a spatial dimension compared to univariate and multivariate forecasting. **In spatio-temporal forecasting, if each measurement point has only one variable, it is equivalent to multivariate forecasting. Therefore, the distinction between spatio-temporal forecasting and multivariate forecasting is not clear. Spatio-temporal models can usually be directly applied to multivariate forecasting, and multivariate models can also be used for spatio-temporal forecasting with minor modifications. Here we also classify solely based on the model's description in the original paper.**
*  univariate time series forecasting: , where  is the history length,  is the prediction horizon length.
*  multivariate time series forecasting: , where  is the number of variables (channels).
*  spatio-temporal forecasting: , where  is the spatial dimension (number of measurement points). However, some spatio-temporal models set the output channel to 1, and even the input channel to 1, which is actually equivalent to multivariate time series forecasting.
*  irregular time series: observation/sampling times are irregular.
## News.
🚩 2023/11/1: **I have marked some recommended papers with 🌟 (Just my personal preference 😉).**
🚩 2023/11/1: **I have added a new category : models specifically designed for irregular time series.**
🚩 2023/11/1: **I also recommend you to check out some other GitHub repositories about awesome time series papers: [time-series-transformers-review](https://github.com/qingsongedu/time-series-transformers-review), [awesome-AI-for-time-series-papers](https://github.com/qingsongedu/awesome-AI-for-time-series-papers), [time-series-papers](https://github.com/xiyuanzh/time-series-papers), [deep-learning-time-series](https://github.com/Alro10/deep-learning-time-series).**
🚩 2023/11/3: **There are some popular toolkits or code libraries that integrate many time series models: [PyPOTS](https://github.com/WenjieDu/PyPOTS), [Time-Series-Library](https://github.com/thuml/Time-Series-Library), [Prophet](https://github.com/facebook/prophet), [Darts](https://github.com/unit8co/darts), [Kats](https://github.com/facebookresearch/Kats), [tsai](https://github.com/timeseriesAI/tsai), [GluonTS](https://github.com/awslabs/gluonts), [PyTorchForecasting](https://github.com/jdb78/pytorch-forecasting), [tslearn](https://github.com/tslearn-team/tslearn), [AutoGluon](https://github.com/autogluon/autogluon), [flow-forecast](https://github.com/AIStream-Peelout/flow-forecast), [PyFlux](https://github.com/RJT1990/pyflux).**
🚩 2023/12/28: **Since the topic of LLM(Large Language Model)+TS(Time Series) has been popular recently, I have introduced a category (LLM) to include related papers. This is distinguished from the Pretrain category. Pretrain mainly contains papers which design agent tasks (contrastive or generative) suitable for time series, and only use large-scale time series data for pre-training.**
🚩 2024/4/1: **Some researchers have introduced the recently popular [Mamba](https://arxiv.org/abs/2312.00752) model into the field of time series forecasting, which can be found in the SSM (State Space Model) table.**
🚩 2024/6/7: **I will mark some hot papers with 🔥 (Papers with over 100 citations).**
🚩 2024/9/10: **I am preparing to open [a new GitHub repository](https://github.com/ddz16/VSTFpaper) to collect papers related to Video Spatio-Temporal Forecasting (VSTF). The mapping function for VSTF is , where  and  are the height and width of each frame. Compared to spatio-temporal forecasting mentioned before, it replaces  with . This setup is commonly used in video prediction and weather forecasting. Stay tuned!**
🚩 2024/10/23: **I have introduced a new table (Multimodal) to include papers that utilize multimodal data (such as relevant text) to assist in forecasting and a new table (KAN) to include papers that utilize Kolmogorov–Arnold Networks.**
🚩 2024/12/30: **Christoph Bergmeir raised insightful questions about the benchmarks in the field of time series forecasting during [his talk at NIPS 2024](https://cbergmeir.com/talks/neurips2024/). This critique is highly valuable and well worth watching. I strongly recommend watching this talk before embarking on time series research.**
🚩 2025/06/02: **I have divided the papers in the Pretrain & Representation Table into two groups: Representation Learning and Foundation Models. The former focuses on designing pretrain tasks (such as contrastive learning and masked modeling), while the latter typically provides time series foundation models pre-trained on large-scale time series datasets.**
Survey & Benchmark.
Date|Method|Conference|Paper Title and Paper Interpretation (In Chinese)|Code
-----|----|-----|-----|-----
15-11-23|[Multi-step](https://ieeexplore.ieee.org/abstract/document/7422387)|ACOMP 2015|Comparison of Strategies for Multi-step-Ahead Prediction of Time Series Using Neural Network|None
19-06-11|[STData](https://arxiv.org/abs/1906.04928)🔥 | TKDE 2020|Deep learning for spatio-temporal data mining: A survey|None
19-06-20|[DL](https://ieeexplore.ieee.org/abstract/document/8742529)🔥 | SENSJ 2019|A Review of Deep Learning Models for Time Series Prediction|None
20-09-27|[DL](https://arxiv.org/abs/2004.13408)🔥 |Arxiv 2020|Time Series Forecasting With Deep Learning: A Survey|None
22-02-15|[Transformer](https://arxiv.org/abs/2202.07125)🔥 |IJCAI 2023|Transformers in Time Series: A Survey|[PaperList](https://github.com/qingsongedu/time-series-transformers-review)
23-03-25|[STGNN](https://arxiv.org/abs/2303.14483)🔥 |TKDE 2023|Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey|None
23-05-01|[Diffusion](https://arxiv.org/abs/2305.00624)|Arxiv 2023|Diffusion Models for Time Series Applications: A Survey|None
23-06-14|[LargeST](https://arxiv.org/abs/2306.08259)|NIPS 2023|LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting|[largest](https://github.com/liuxu77/largest)
23-06-16|[SSL](https://arxiv.org/abs/2306.10125)🔥|TPAMI 2024|Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects|None
23-06-20|[OpenSTL](https://arxiv.org/abs/2306.11249)|NIPS 2023|OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning|[Benchmark](https://github.com/chengtan9907/OpenSTL)
23-07-07|[GNN](https://arxiv.org/abs/2307.03759)🔥|TPAMI 2024|A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection|[PaperList](https://github.com/KimMeen/Awesome-GNN4TS)
23-10-09|[BasicTS](https://arxiv.org/abs/2310.06119)|TKDE 2024|Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis|[BasicTS](https://github.com/GestaltCogTeam/BasicTS)
23-10-11|[ProbTS](https://arxiv.org/abs/2310.07446)|Arxiv 2023|ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons|[ProbTS](https://github.com/microsoft/probts)
23-10-16|[LargeModel](https://arxiv.org/abs/2310.10196)|Arxiv 2023|Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook|[PaperList](https://github.com/qingsongedu/Awesome-TimeSeries-SpatioTemporal-LM-LLM)
23-12-28|[TSPP](https://arxiv.org/abs/2312.17100)|Arxiv 2023|TSPP: A Unified Benchmarking Tool for Time-series Forecasting|[TSPP](https://github.com/NVIDIA/DeepLearningExamples)
24-01-05|[Diffusion](https://arxiv.org/abs/2401.03006)|Arxiv 2024|The Rise of Diffusion Models in Time-Series Forecasting|None
24-02-15|[LLM](https://arxiv.org/abs/2402.10350)🔥|Arxiv 2024|Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review|None
24-03-21|[FM](https://arxiv.org/abs/2403.14735)|KDD 2024|Foundation Models for Time Series Analysis: A Tutorial and Survey| None
24-03-29|[TFB](https://arxiv.org/abs/2403.20150)🌟🔥 |VLDB 2024|TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods|[TFB](https://github.com/decisionintelligence/TFB)
24-04-24|[Mamba-360](https://arxiv.org/abs/2404.16112)|Arxiv 2024|Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges|[Mamba-360](https://github.com/badripatro/mamba360)
24-04-29|[Diffusion](https://arxiv.org/abs/2404.18886)|Arxiv 2024|A Survey on Diffusion Models for Time Series and Spatio-Temporal Data|[PaperList](https://github.com/yyysjz1997/Awesome-TimeSeries-SpatioTemporal-Diffusion-Model)
24-05-03|[FoundationModels](https://arxiv.org/abs/2405.02358)|Arxiv 2024|A Survey of Time Series Foundation Models: Generalizing Time Series Representation with Large Language Model|[PaperList](https://github.com/start2020/awesome-timeseries-llm-fm)
24-07-18|[TSLib](https://arxiv.org/abs/2407.13278)🌟 |Arxiv 2024|Deep Time Series Models: A Comprehensive Survey and Benchmark|[TSLib](https://github.com/thuml/Time-Series-Library)
24-07-29|[Transformer](https://arxiv.org/abs/2407.19784) |Arxiv 2024| Survey and Taxonomy: The Role of Data-Centric AI in Transformer-Based Time Series Forecasting| None
24-10-14|[GIFT-Eval](https://arxiv.org/abs/2410.10393) |Arxiv 2024| GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation | None
24-10-15|[FoundTS](https://arxiv.org/abs/2410.11802) |Arxiv 2024| FoundTS: Comprehensive and Unified Benchmarking of Foundation Models for Time Series Forecasting | [FoundTS](https://anonymous.4open.science/r/FoundTS-C2B0)
24-10-24|[Architecture](https://arxiv.org/abs/2411.05793) |AIR 2025| A Comprehensive Survey of Time Series Forecasting: Architectural Diversity and Open Challenges | None
24-10-29|[STGNN](https://arxiv.org/abs/2410.22377) |Arxiv 2024| A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification | None
24-12-19|[Benchmark](https://arxiv.org/abs/2412.14435)🌟 |AAAI 2025| Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine | [bench](https://github.com/luisroque/bench)
25-02-11|[Physiome-ODE](https://arxiv.org/abs/2502.07489) |ICLR 2025| Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time Series Forecasting Based on Biological ODEs | [Physiome-ODE](https://anonymous.4open.science/r/Phyisiome-ODE-E53D)
25-02-15|[Channel-Strategy](https://arxiv.org/abs/2502.10721) |Arxiv 2025| A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective | [CS4TS](https://github.com/decisionintelligence/CS4TS)
25-02-17|[Positional-Encoding](https://arxiv.org/abs/2502.12370) |Arxiv 2025| Positional Encoding in Transformer-Based Time Series Models: A Survey | [pe-benchmark](https://github.com/imics-lab/positional-encoding-benchmark)
25-02-19|[LTSF](https://arxiv.org/abs/2502.14045) |Arxiv 2025| Position: There are no Champions in Long-Term Time Series Forecasting | None
25-02-26|[FinTSB](https://arxiv.org/abs/2502.18834) |Arxiv 2025| FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting | [FinTSB](https://github.com/TongjiFinLab/FinTSB)
25-03-13|[DL](https://arxiv.org/abs/2503.10198) |Arxiv 2025| Deep Learning for Time Series Forecasting: A Survey | None
25-04-05|[FoundationModels](https://arxiv.org/abs/2504.04011) |Arxiv 2025| Foundation Models for Time Series: A Survey | None
25-04-10|[Survey](https://www.techrxiv.org/users/909144/articles/1283131-a-comprehensive-survey-of-time-series-forecasting-concepts-challenges-and-future-directions) |Arxiv 2025| A Comprehensive Survey of Time Series Forecasting: Concepts, Challenges, and Future Directions | [PaperList](https://github.com/USTCAGI/Awesome-Papers-Time-Series-Forecasting)
Transformer.
Date|Method|Type|Conference|Paper Title and Paper Interpretation (In Chinese)|Code
-----|----|----|-----|-----|-----
19-06-29|[LogTrans](https://arxiv.org/abs/1907.00235)🔥 |  |NIPS 2019|Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting|[flowforecast](https://github.com/AIStream-Peelout/flow-forecast/blob/master/flood_forecast/transformer_xl/transformer_bottleneck.py) |
19-12-19|[TFT](https://arxiv.org/abs/1912.09363)🌟🔥 |  |IJoF 2021|[Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://www.zhihu.com/question/451816360/answer/2319401126)|[tft](https://github.com/google-research/google-research/tree/master/tft) |
20-01-23|[InfluTrans](https://arxiv.org/abs/2001.08317)🔥 |  |Arxiv 2020|[Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case](https://towardsdatascience.com/how-to-make-a-pytorch-transformer-for-time-series-forecasting-69e073d4061e)|[influenza transformer](https://github.com/KasperGroesLudvigsen/influenza_transformer) |
20-06-05|[AST](https://proceedings.neurips.cc/paper/2020/file/c6b8c8d762da15fa8dbbdfb6baf9e260-Paper.pdf) 🔥 |  |NIPS 2020|Adversarial Sparse Transformer for Time Series Forecasting|[AST](https://github.com/hihihihiwsf/AST)
20-12-14|[Informer](https://arxiv.org/abs/2012.07436)🌟🔥|  |AAAI 2021|[Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://zhuanlan.zhihu.com/p/467523291)|[Informer](https://github.com/zhouhaoyi/Informer2020)
21-05-22|[ProTran](https://proceedings.neurips.cc/paper_files/paper/2021/file/c68bd9055776bf38d8fc43c0ed283678-Paper.pdf)|  |NIPS 2021|Probabilistic Transformer for Time Series Analysis|None
21-06-24|[Autoformer](https://arxiv.org/abs/2106.13008)🌟🔥|  |NIPS 2021|[Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://zhuanlan.zhihu.com/p/385066440)|[Autoformer](https://github.com/thuml/Autoformer)
21-09-17|[Aliformer](https://arxiv.org/abs/2109.08381)|  | Arxiv 2021 | From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba | None
21-10-05|[Pyraformer](https://openreview.net/pdf?id=0EXmFzUn5I)🔥|  |ICLR 2022|[Pyraformer: Low-complexity Pyramidal Attention for Long-range Time Series Modeling and Forecasting](https://zhuanlan.zhihu.com/p/467765457)|[Pyraformer](https://github.com/alipay/Pyraformer)
22-01-14|[Preformer](https://arxiv.org/abs/2202.11356)🔥|  |ICASSP 2023|[Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecasting](https://zhuanlan.zhihu.com/p/536398013)|[Preformer](https://github.com/ddz16/Preformer)
22-01-30|[FEDformer](https://arxiv.org/abs/2201.12740)🌟🔥 |  |ICML 2022|[FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://zhuanlan.zhihu.com/p/528131016)|[FEDformer](https://github.com/MAZiqing/FEDformer)
22-02-03|[ETSformer](https://arxiv.org/abs/2202.01381) 🔥|  |Arxiv 2022|[ETSformer: Exponential Smoothing Transformers for Time-series Forecasting](https://blog.salesforceairesearch.com/etsformer-time-series-forecasting/)|[etsformer](https://github.com/salesforce/etsformer)
22-02-07|[TACTiS](https://arxiv.org/abs/2202.03528)|  |ICML 2022|TACTiS: Transformer-Attentional Copulas for Time Series|[TACTiS](https://github.com/ServiceNow/tactis)
22-04-28|[Triformer](https://arxiv.org/abs/2204.13767)|  |IJCAI 2022|[Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting](https://blog.csdn.net/zj_18706809267/article/details/125048492)| [Triformer](https://github.com/razvanc92/triformer)
22-05-27|[TDformer](https://arxiv.org/abs/2212.08151)|  |NIPSW 2022|[First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting](https://zhuanlan.zhihu.com/p/596022160)|[TDformer](https://github.com/BeBeYourLove/TDformer)
22-05-28|[Non-stationary Transformer](https://arxiv.org/abs/2205.14415) 🔥 |  |NIPS 2022|[Non-stationary Transformers: Rethinking the Stationarity in Time Series Forecasting](https://zhuanlan.zhihu.com/p/535931701)|[Non-stationary Transformers](https://github.com/thuml/Nonstationary_Transformers)
22-06-08|[Scaleformer](https://arxiv.org/abs/2206.04038)|  |ICLR 2023|[Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting](https://zhuanlan.zhihu.com/p/535556231)|[Scaleformer](https://github.com/BorealisAI/scaleformer)
22-08-14|[Quatformer](https://dl.acm.org/doi/abs/10.1145/3534678.3539234)|  |KDD 2022|Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting|[Quatformer](https://github.com/DAMO-DI-ML/KDD2022-Quatformer)
22-08-30|[Persistence Initialization](https://arxiv.org/abs/2208.14236)|  |Arxiv 2022|[Persistence Initialization: A novel adaptation of the Transformer architecture for Time Series Forecasting](https://zhuanlan.zhihu.com/p/582419707)|None
22-09-08|[W-Transformers](https://arxiv.org/abs/2209.03945)|  |ICMLA 2022|[W-Transformers: A Wavelet-based Transformer Framework for Univariate Time Series Forecasting](https://zhuanlan.zhihu.com/p/582419707)|[w-transformer](https://github.com/capwidow/w-transformer)
22-09-22|[Crossformer](https://openreview.net/forum?id=vSVLM2j9eie) 🔥 |  |ICLR 2023|Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting|[Crossformer](https://github.com/Thinklab-SJTU/Crossformer)
22-09-22|[PatchTST](https://arxiv.org/abs/2211.14730)🌟🔥|  |ICLR 2023|[A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://zhuanlan.zhihu.com/p/602332939)|[PatchTST](https://github.com/yuqinie98/patchtst)
22-11-29|[AirFormer](https://arxiv.org/abs/2211.15979)|  | AAAI 2023 |AirFormer: Predicting Nationwide Air Quality in China with Transformers | [AirFormer](https://github.com/yoshall/airformer)
22-12-06|[TVT](https://arxiv.org/abs/2212.02789) |  |Arxiv 2022 | A K-variate Time Series Is Worth K Words: Evolution of the Vanilla Transformer Architecture for Long-term Multivariate Time Series Forecasting | None
23-01-05|[Conformer](https://arxiv.org/abs/2301.02068)|  |ICDE 2023|Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution|[Conformer](https://github.com/PaddlePaddle/PaddleSpatial/tree/main/research/Conformer)
23-01-19|[PDFormer](https://arxiv.org/abs/2301.07945)🔥|  | AAAI 2023 | PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction | [PDFormer](https://github.com/BUAABIGSCity/PDFormer)
23-03-01|[ViTST](https://arxiv.org/abs/2303.12799)|  | NIPS 2023 | Time Series as Images: Vision Transformer for Irregularly Sampled Time Series |[ViTST](https://github.com/Leezekun/ViTST)
23-05-20|[CARD](https://arxiv.org/abs/2305.12095)|  |ICLR 2024| CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting | [CARD](https://github.com/wxie9/card)
23-05-24|[JTFT](https://arxiv.org/abs/2305.14649) |  | NN 2024 | A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecasting | None
23-05-30|[HSTTN](https://arxiv.org/abs/2305.18724) |  | IJCAI 2023 | Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer | None
23-05-30|[Client](https://arxiv.org/abs/2305.18838) |  | Arxiv 2023 | Client: Cross-variable Linear Integrated Enhanced Transformer for Multivariate Long-Term Time Series Forecasting | [Client](https://github.com/daxin007/client)
23-05-30|[Taylorformer](https://arxiv.org/abs/2305.19141) |  | Arxiv 2023 | Taylorformer: Probabilistic Predictions for Time Series and other Processes | [Taylorformer](https://www.dropbox.com/s/vnxuwq7zm7m9bj8/taylorformer.zip?dl=0)
23-06-05|[Corrformer](https://www.nature.com/articles/s42256-023-00667-9)🌟 |  | NMI 2023 | [Interpretable weather forecasting for worldwide stations with a unified deep model](https://zhuanlan.zhihu.com/p/635902919) | [Corrformer](https://github.com/thuml/Corrformer)
23-06-14|[GCformer](https://arxiv.org/abs/2306.08325) |  | CIKM 2023 | GCformer: An Efficient Solution for Accurate and Scalable Long-Term Multivariate Time Series Forecasting | [GCformer](https://github.com/zyj-111/gcformer)
23-07-04 | [SageFormer](https://arxiv.org/abs/2307.01616) |  | IoT 2024 | SageFormer: Series-Aware Graph-Enhanced Transformers for Multivariate Time Series Forecasting | [SageFormer](https://github.com/zhangzw16/SageFormer)
23-07-10 | [DifFormer](https://ieeexplore.ieee.org/abstract/document/10177239) |  | TPAMI 2023 | DifFormer: Multi-Resolutional Differencing Transformer With Dynamic Ranging for Time Series Analysis | None
23-07-27 | [HUTFormer](https://arxiv.org/abs/2307.14596) |  | Arxiv 2023 | HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting | None
23-08-07 | [DSformer](https://arxiv.org/abs/2308.03274) |  | CIKM 2023 | DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction | None
23-08-09 | [SBT](https://arxiv.org/abs/2308.04637) |  | KDD 2023 | Sparse Binary Transformers for Multivariate Time Series Modeling | None
23-08-09 | [PETformer](https://arxiv.org/abs/2308.04791) |  | Arxiv 2023 | PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformer | None
23-10-02 | [TACTiS-2](https://browse.arxiv.org/abs/2310.01327)|  | ICLR 2024 | TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series | None
23-10-03 | [PrACTiS](https://browse.arxiv.org/abs/2310.01720)|  | Arxiv 2023 | PrACTiS: Perceiver-Attentional Copulas for Time Series | None
23-10-10 | [iTransformer](https://arxiv.org/abs/2310.06625)🔥 |  | ICLR 2024 | [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://zhuanlan.zhihu.com/p/662250788) | [iTransformer](https://github.com/thuml/iTransformer)
23-10-26 | [ContiFormer](https://seqml.github.io/contiformer/)|  | NIPS 2023 | ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling | [ContiFormer](https://github.com/microsoft/SeqML/tree/main/ContiFormer)
23-10-31 | [BasisFormer](https://arxiv.org/abs/2310.20496)|  | NIPS 2023 | BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis | [basisformer](https://github.com/nzl5116190/basisformer)
23-11-07 | [MTST](https://arxiv.org/abs/2311.04147)|  | AISTATS 2023 | Multi-resolution Time-Series Transformer for Long-term Forecasting | [MTST](https://github.com/networkslab/MTST)
23-11-30 | [MultiResFormer](https://arxiv.org/abs/2311.18780)|  | Arxiv 2023 | MultiResFormer: Transformer with Adaptive Multi-Resolution Modeling for General Time Series Forecasting | None
23-12-10 | [FPPformer](https://arxiv.org/abs/2312.05792)|  | IOT 2023 | Take an Irregular Route: Enhance the Decoder of Time-Series Forecasting Transformer | [FPPformer](https://github.com/OrigamiSL/FPPformer)
23-12-11 | [Dozerformer](https://arxiv.org/abs/2312.06874)|  | Arxiv 2023 | Dozerformer: Sequence Adaptive Sparse Transformer for Multivariate Time Series Forecasting | None
23-12-11 | [CSformer](https://arxiv.org/abs/2312.06220)|  | Arxiv 2023 | Dance of Channel and Sequence: An Efficient Attention-Based Approach for Multivariate Time Series Forecasting | None
23-12-23 | [MASTER](https://arxiv.org/abs/2312.15235)|  | AAAI 2024 | MASTER: Market-Guided Stock Transformer for Stock Price Forecasting | [MASTER](https://github.com/SJTU-Quant/MASTER)
23-12-30 | [PCA+former](https://arxiv.org/abs/2401.00230)|  | Arxiv 2023 | Transformer Multivariate Forecasting: Less is More? | None
24-01-16 | [PDF](https://openreview.net/forum?id=dp27P5HBBt)|  | ICLR 2024 | [Periodicity Decoupling Framework for Long-term Series Forecasting](https://zhuanlan.zhihu.com/p/699708089) | [PDF](https://github.com/Hank0626/PDF)
24-01-16 | [Pathformer](https://openreview.net/forum?id=lJkOCMP2aW)|  | ICLR 2024 | Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting | [pathformer](https://github.com/decisionintelligence/pathformer)
24-01-16 | [VQ-TR](https://openreview.net/forum?id=IxpTsFS7mh)|  | ICLR 2024 | VQ-TR: Vector Quantized Attention for Time Series Forecasting | None
24-01-22 | [HDformer](https://arxiv.org/abs/2401.11929)|  | Arxiv 2024 | The Bigger the Better? Rethinking the Effective Model Scale in Long-term Time Series Forecasting | None
24-02-04 | [Minusformer](https://arxiv.org/abs/2402.02332)|  | Arxiv 2024 | Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals | [Minusformer](https://github.com/anoise/minusformer)
24-02-08 | [AttnEmbed](https://arxiv.org/abs/2402.05370)|  | Arxiv 2024 | Attention as Robust Representation for Time Series Forecasting | [AttnEmbed](https://anonymous.4open.science/r/AttnEmbed-7430)
24-02-15 | [SAMformer](https://arxiv.org/abs/2402.10198)|  | ICML 2024 | [Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention](https://romilbert.github.io/samformer_slides.pdf) | [SAMformer](https://github.com/romilbert/samformer)
24-02-25 | [PDETime](https://arxiv.org/abs/2402.16913)|  | Arxiv 2024 | PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations | None
24-02-29 | [TimeXer](https://arxiv.org/abs/2402.19072)|  | NIPS 2024 | TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables | [TimeXer](https://github.com/thuml/TimeXer)
24-03-05 | [InjectTST](https://arxiv.org/abs/2403.02814)|  | Arxiv 2024 | InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting | None
24-03-13 | [Caformer](https://arxiv.org/abs/2403.08572)|  | Arxiv 2024 | Caformer: Rethinking Time Series Analysis from Causal Perspective | None
24-03-14 | [MCformer](https://arxiv.org/abs/2403.09223)|  | Arxiv 2024 | MCformer: Multivariate Time Series Forecasting with Mixed-Channels Transformer | None
24-04-08 | [ATFNet](https://arxiv.org/abs/2404.05192)|  | Arxiv 2024 | ATFNet: Adaptive Time-Frequency Ensembled Network for Long-term Time Series Forecasting | [ATFNet](https://github.com/YHYHYHYHYHY/ATFNet)
24-04-12 | [TSLANet](https://arxiv.org/abs/2404.08472)|  | ICML 2024 | TSLANet: Rethinking Transformers for Time Series Representation Learning | [TSLANet](https://github.com/emadeldeen24/TSLANet)
24-04-16 | [T2B-PE](https://arxiv.org/abs/2404.10337)|  | Arxiv 2024 | Intriguing Properties of Positional Encoding in Time Series Forecasting | [T2B-PE](https://github.com/jlu-phyComputer/T2B-PE)
24-05-14 | [DGCformer](https://arxiv.org/abs/2405.08440)|  | Arxiv 2024 | DGCformer: Deep Graph Clustering Transformer for Multivariate Time Series Forecasting | None
24-05-19 | [VCformer](https://arxiv.org/abs/2405.11470)|  | Arxiv 2024 | VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting | [VCformer](https://github.com/CSyyn/VCformer)
24-05-22 | [GridTST](https://arxiv.org/abs/2405.13810)|  | Arxiv 2024 | Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers | [GridTST](https://github.com/Hannibal046/GridTST)
24-05-23 | [ICTSP](https://arxiv.org/abs/2405.14982)|  | ICLR 2025 | In-context Time Series Predictor | None
24-05-27 | [CATS](https://arxiv.org/abs/2405.16877)|  | NIPS 2024 | Are Self-Attentions Effective for Time Series Forecasting? | [CATS](https://github.com/dongbeank/CATS)
24-06-06 | [TwinS](https://arxiv.org/abs/2406.03710)|  | Arxiv 2024 | TwinS: Revisiting Non-Stationarity in Multivariate Time Series Forecasting | None
24-06-07 | [UniTST](https://arxiv.org/abs/2406.04975)|  | Arxiv 2024 | UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting | None
24-06-11 | [DeformTime](https://arxiv.org/abs/2406.07438)|  | Arxiv 2024 | DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting | [DeformTime](https://github.com/ClaudiaShu/DeformTime)
24-06-13 | [Fredformer](https://arxiv.org/abs/2406.09009)|  | KDD 2024 | Fredformer: Frequency Debiased Transformer for Time Series Forecasting | [Fredformer](https://github.com/chenzrg/fredformer)
24-07-18 | [FSatten-SOatten](https://arxiv.org/abs/2407.13806)|  | Arxiv 2024 | Revisiting Attention for Multivariate Time Series Forecasting | [FSatten-SOatten](https://github.com/Joeland4/FSatten-SOatten)
24-07-18 | [MTE](https://arxiv.org/abs/2407.15869)|  | Arxiv 2024 | Long Input Sequence Network for Long Time Series Forecasting | [MTE](https://github.com/Houyikai/MTE)
24-07-31 | [FreqTSF](https://arxiv.org/abs/2407.21275)|  | Arxiv 2024 | FreqTSF: Time Series Forecasting Via Simulating Frequency Kramer-Kronig Relations | None
24-08-05 | [DRFormer](https://arxiv.org/abs/2408.02279)|  | CIKM 2024 | DRFormer: Multi-Scale Transformer Utilizing Diverse Receptive Fields for Long Time-Series Forecasting | [DRFormer](https://github.com/ruixindingECNU/DRFormer)
24-08-08 | [STHD](https://arxiv.org/abs/2408.04245)|  | CIKM 2024 | Scalable Transformer for High Dimensional Multivariate Time Series Forecasting | [STHD](https://github.com/xinzzzhou/ScalableTransformer4HighDimensionMTSF)
24-08-16 | [S3Attention](https://arxiv.org/abs/2408.08567)|  | Arxiv 2024 | S3Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching | [S3Attention](https://github.com/wxie9/S3Attention)
24-08-19 | [PMformer](https://arxiv.org/abs/2408.09703)|  | Arxiv 2024 | Partial-Multivariate Model for Forecasting | None
24-08-19 | [sTransformer](https://arxiv.org/abs/2408.09723)|  | Arxiv 2024 | sTransformer: A Modular Approach for Extracting Inter-Sequential and Temporal Information for Time-Series Forecasting | None
24-08-20 | [PRformer](https://arxiv.org/abs/2408.10483)|  | Arxiv 2024 | PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting | [PRformer](https://github.com/usualheart/PRformer)
24-09-25 | [DeformableTST](https://openreview.net/forum?id=B1Iq1EOiVU)|  | NIPS 2024 | DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching | [DeformableTST](https://github.com/luodhhh/DeformableTST)
24-09-30 | [CTLPE](https://arxiv.org/abs/2409.20092)|  | Arxiv 2024 | Continuous-Time Linear Positional Embedding for Irregular Time Series Forecasting | None
24-10-02 | [TiVaT](https://arxiv.org/abs/2410.01531)|  | Arxiv 2024 | TiVaT: Joint-Axis Attention for Time Series Forecasting with Lead-Lag Dynamics | None
24-10-04 | [ARMA](https://arxiv.org/abs/2410.03159)|  | Arxiv 2024 | Autoregressive Moving-average Attention Mechanism for Time Series Forecasting | [ARMA-Attention](https://github.com/LJC-FVNR/ARMA-Attention)
24-10-06 | [TimeBridge](https://arxiv.org/abs/2410.04442)|  | ICML 2025 | TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting | [TimeBridge](https://github.com/Hank0626/TimeBridge)
24-10-30 | [WaveRoRA](https://arxiv.org/abs/2410.22649)|  | Arxiv 2024 | WaveRoRA: Wavelet Rotary Route Attention for Multivariate Time Series Forecasting | None
24-10-31 | [Ada-MSHyper](https://arxiv.org/abs/2410.23992)|  | NIPS 2024 | Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting | [Ada-MSHyper](https://github.com/shangzongjiang/Ada-MSHyper)
24-11-03 | [PSformer](https://arxiv.org/abs/2411.01419)|  | Arxiv 2024 | PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecasting | None
24-11-04 | [ElasTST](https://arxiv.org/abs/2411.01842)|  | NIPS 2024 | ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer | [elastst](https://github.com/microsoft/ProbTS/tree/elastst)
24-11-07 | [Peri-midFormer](https://arxiv.org/abs/2411.04554)|  | NIPS 2024 | Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis | [Peri-midFormer](https://github.com/WuQiangXDU/Peri-midFormer)
24-12-02 | [MuSiCNet](https://arxiv.org/abs/2412.01063)|  | IJCAIW 2024 | MuSiCNet: A Gradual Coarse-to-Fine Framework for Irregularly Sampled Multivariate Time Series Analysis | None
24-12-04 | [HOT](https://arxiv.org/abs/2412.02919)|  | Arxiv 2024 | Higher Order Transformers: Efficient Attention Mechanism for Tensor Structured Data | None
24-12-16 | [EDformer](https://arxiv.org/abs/2412.12227)|  | Arxiv 2024 | EDformer: Embedded Decomposition Transformer for Interpretable Multivariate Time Series Predictions | [EDformer](https://github.com/sanjaylopa22/EDformer-Main)
24-12-17 | [TimeCHEAT](https://arxiv.org/abs/2412.12886)|  | AAAI 2025 | TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis | None
24-12-25 | [Ister](https://arxiv.org/abs/2412.18798)|  | Arxiv 2024 | Ister: Inverted Seasonal-Trend Decomposition Transformer for Explainable Multivariate Time Series Forecasting | None
25-01-06 | [Sensorformer](https://arxiv.org/abs/2501.03284)|  | Arxiv 2025 | Sensorformer: Cross-patch attention with global-patch compression is effective for high-dimensional multivariate time series forecasting | [Sensorformer](https://github.com/BigYellowTiger/Sensorformer)
25-01-14 | [LiPFormer](https://arxiv.org/abs/2501.10448)|  | ICDE 2025 | Towards Lightweight Time Series Forecasting: a Patch-wise Transformer with Weak Data Enriching | None
25-01-22 | [T-Graphormer](https://arxiv.org/abs/2501.13274)|  | Arxiv 2025 | T-Graphormer: Using Transformers for Spatiotemporal Forecasting | None
25-01-23 | [FreEformer](https://arxiv.org/abs/2501.13989)|  | Arxiv 2025 | FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecasting | None
25-01-23 | [SimMTSF](https://openreview.net/forum?id=oANkBaVci5)|  | ICLR 2025 | A Simple Baseline for Multivariate Time Series Forecasting | None
25-01-24 | [VarDrop](https://arxiv.org/abs/2501.14183)|  | AAAI 2025 | VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting | [VarDrop](https://github.com/kaist-dmlab/VarDrop)
25-01-28 | [Spikformer](https://arxiv.org/abs/2501.16745)|  | Arxiv 2025 | Toward Relative Positional Encoding in Spiking Transformers | None
25-02-10 | [Powerformer](https://arxiv.org/abs/2502.06151)|  | Arxiv 2025 | Powerformer: A Transformer with Weighted Causal Attention for Time-series Forecasting | None
25-02-11 | [SAMoVAR](https://arxiv.org/abs/2502.07244)|  | Arxiv 2025 | Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting | [SAMoVAR](https://github.com/LJC-FVNR/Structural-Aligned-Mixture-of-VAR)
25-02-12 | [HDT](https://arxiv.org/abs/2502.08302)|  | AAAI 2025 | HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting | [HDT](https://github.com/hdtkk/HDT)
25-02-13 | [FaCT](https://arxiv.org/abs/2502.09683)|  | Arxiv 2025 | Channel Dependence, Limited Lookback Windows, and the Simplicity of Datasets: How Biased is Time Series Forecasting? | None
25-02-17 | [S2TX](https://arxiv.org/abs/2502.11340)|  | Arxiv 2025 | S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting | None
25-02-19 | [AutoFormer-TS](https://arxiv.org/abs/2502.13721)|  | Arxiv 2025 | Learning Novel Transformer Architecture for Time-series Forecasting | None
25-02-27 | [PFformer](https://arxiv.org/abs/2502.20571)|  | PAKDD 2025 | PFformer: A Position-Free Transformer Variant for Extreme-Adaptive Multivariate Time Series Forecasting | None
25-03-03 | [ContexTST](https://arxiv.org/abs/2503.01157)|  | Arxiv 2025 | Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting | None
25-03-07 | [PPDformer](https://ieeexplore.ieee.org/document/10890581)|  | ICASSP 2025 | PPDformer: Channel-Specific Periodic Patch Division for Time Series Forecasting | [PPDformer](https://github.com/damonwan1/PPDformer)
25-03-10 | [Attn-L-Reg](https://arxiv.org/abs/2503.06867)|  | Arxiv 2025 | Enhancing Time Series Forecasting via Logic-Inspired Regularization | None
25-03-11 | [MFRS](https://arxiv.org/abs/2503.08328)|  | Arxiv 2025 | MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecasting | [MFRS](https://github.com/yuliang555/MFRS)
25-03-13 | [EiFormer](https://arxiv.org/abs/2503.10858)|  | Arxiv 2025 | Towards Efficient Large Scale Spatial-Temporal Time Series Forecasting via Improved Inverted Transformers | None
25-03-22 | [Sentinel](https://arxiv.org/abs/2503.17658)|  | Arxiv 2025 | Sentinel: Multi-Patch Transformer with Temporal and Channel Attention for Time Series Forecasting | None
25-03-31 | [CITRAS](https://arxiv.org/abs/2503.24007)|  | Arxiv 2025 | CITRAS: Covariate-Informed Transformer for Time Series Forecasting | None
25-04-02 | [Times2D](https://arxiv.org/abs/2504.00118)|  | AAAI 2025 | Times2D: Multi-Period Decomposition and Derivative Mapping for General Time Series Forecasting | [Times2D](https://github.com/Tims2D/Times2D)
25-04-17 | [TimeCapsule](https://arxiv.org/abs/2504.12721)|  | KDD 2025 | TimeCapsule: Solving the Jigsaw Puzzle of Long-Term Time Series Forecasting with Compressed Predictive Representations | None
25-04-26 | [TSRM](https://arxiv.org/abs/2504.18878)|  | Arxiv 2025 | TSRM: A Lightweight Temporal Feature Encoding Architecture for Time Series Forecasting and Imputation | [TSRM](https://github.com/RobertLeppich/TSRM)
25-05-01 | [Gateformer](https://arxiv.org/abs/2505.00307)|  | Arxiv 2025 | Gateformer: Advancing Multivariate Time Series Forecasting through Temporal and Variate-Wise Attention with Gated Representations | [Gateformer](https://github.com/nyuolab/gateformer)
25-05-04 | [CASA](https://arxiv.org/abs/2505.02011)|  | IJCAI 2025 | CASA: CNN Autoencoder-based Score Attention for Efficient Multivariate Long-term Time-series Forecasting | [casa](https://github.com/lmh9507/casa)
25-05-05 | [SCFormer](https://arxiv.org/abs/2505.02655)|  | Arxiv 2025 | SCFormer: Structured Channel-wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting | [SCFormer](https://github.com/ShiweiGuo1995/SCFormer)
25-05-19 | [TQNet](https://arxiv.org/abs/2505.12917)|  | ICML 2025 | Temporal Query Network for Efficient Multivariate Time Series Forecasting | [TQNet](https://github.com/ACAT-SCUT/TQNet)
25-05-20 | [LMHR](https://arxiv.org/abs/2505.14737)|  | Arxiv 2025 | Leveraging Multivariate Long-Term History Representation for Time Series Forecasting | None
25-05-21 | [Sonnet](https://arxiv.org/abs/2505.15312)|  | Arxiv 2025 | Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting | [Sonnet](https://github.com/ClaudiaShu/Sonnet)
25-05-22 | [CAIFormer](https://arxiv.org/abs/2505.16308)|  | Arxiv 2025 | CAIFormer: A Causal Informed Transformer for Multivariate Time Series Forecasting | None
25-06-10 | [ChannelTokenFormer](https://arxiv.org/abs/2506.08660) |  | Arxiv 2025 | Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness | None
RNN.
Date|Method|Type|Conference|Paper Title and Paper Interpretation (In Chinese)|Code
-----|----|-----|-----|-----|-----
17-03-21|[LSTNet](https://arxiv.org/abs/1703.07015)🌟🔥 |  |SIGIR 2018|[Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://zhuanlan.zhihu.com/p/467944750)|[LSTNet](https://github.com/laiguokun/LSTNet) |
17-04-07|[DA-RNN](https://arxiv.org/abs/1704.02971)🔥 |  |IJCAI 2017| A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction | [DARNN](https://github.com/sunfanyunn/DARNN) |
17-04-13|[DeepAR](https://arxiv.org/abs/1704.04110)🌟🔥 |  |IJoF 2019|[DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://zhuanlan.zhihu.com/p/542066911)|[DeepAR](https://github.com/brunoklein99/deepar) |
17-11-29|[MQRNN](https://arxiv.org/abs/1711.11053)🔥 |  |NIPSW 2017|A Multi-Horizon Quantile Recurrent Forecaster|[MQRNN](https://github.com/tianchen101/MQRNN) |
18-06-23|[mWDN](https://arxiv.org/abs/1806.08946)🔥 |  |KDD 2018|Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis|[mWDN](https://github.com/yakouyang/Multilevel_Wavelet_Decomposition_Network_Pytorch) |
18-09-06|[MTNet](https://arxiv.org/abs/1809.02105)|  |AAAI 2019| A Memory-Network Based Solution for Multivariate Time-Series Forecasting |[MTNet](https://github.com/Maple728/MTNet) |
19-05-28|[DF-Model](https://arxiv.org/abs/1905.12417)🔥 |  |ICML 2019| Deep Factors for Forecasting | None |
19-07-18|[ESLSTM](https://www.sciencedirect.com/science/article/pii/S0169207019301153)🔥 |  |IJoF 2020|A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting| None |
19-07-25|[MH-TAL](https://dl.acm.org/doi/abs/10.1145/3292500.3330662)🔥 |  |KDD 2019|Multi-Horizon Time Series Forecasting with Temporal Attention Learning| None |
21-11-22|[CRU](https://arxiv.org/abs/2111.11344) |  | ICML 2022 | Modeling Irregular Time Series with Continuous Recurrent Units | [CRU](https://github.com/boschresearch/continuous-recurrent-units)
22-05-16|[C2FAR](https://openreview.net/forum?id=lHuPdoHBxbg)|  |NIPS 2022|[C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting](https://zhuanlan.zhihu.com/p/600602517)|[C2FAR](https://github.com/huaweicloud/c2far_forecasting) |
23-06-02|[RNN-ODE-Adap](https://arxiv.org/abs/2306.01674)|  |Arxiv 2023|Neural Differential Recurrent Neural Network with Adaptive Time Steps| [RNN_ODE_Adap](https://github.com/Yixuan-Tan/RNN_ODE_Adap) |
23-08-22|[SegRNN](https://arxiv.org/abs/2308.11200)|  |Arxiv 2023| SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting| [SegRNN](https://github.com/lss-1138/SegRNN) |
23-10-05|[PA-RNN](https://arxiv.org/abs/2310.03243)|  |NIPS 2023| Sparse Deep Learning for Time Series Data: Theory and Applications | None |
23-11-03|[WITRAN](https://openreview.net/forum?id=y08bkEtNBK)|  |NIPS 2023| WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting | [WITRAN](https://github.com/Water2sea/WITRAN) |
23-12-14|[DAN](https://arxiv.org/abs/2312.08763)|  |AAAI 2024| Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting | [DAN](https://github.com/davidanastasiu/dan) |
23-12-22|[SutraNets](https://arxiv.org/abs/2312.14880)|  |NIPS 2023| SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting | None |
24-01-17|[RWKV-TS](https://arxiv.org/abs/2401.09093)|  |Arxiv 2024| RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks | [RWKV-TS](https://github.com/howard-hou/RWKV-TS) |
24-06-04|[TGLRN](https://arxiv.org/abs/2406.02726)|  |Arxiv 2024| Temporal Graph Learning Recurrent Neural Network for Traffic Forecasting | None |
24-06-29|[CONTIME](https://arxiv.org/abs/2407.01622)|  |KDD 2024| Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization | [CONTIME](https://github.com/sheoyon-jhin/CONTIME) |
24-07-14|[xLSTMTime](https://arxiv.org/abs/2407.10240)|  |Arxiv 2024| xLSTMTime: Long-term Time Series Forecasting With xLSTM | [xLSTMTime](https://github.com/muslehal/xLSTMTime) |
24-07-29|[TFFM](https://arxiv.org/abs/2407.19697)|  |CIKM 2024| Multiscale Representation Enhanced Temporal Flow Fusion Model for Long-Term Workload Forecasting | None |
24-08-19|[P-sLSTM](https://arxiv.org/abs/2408.10006)|  |Arxiv 2024| Unlocking the Power of LSTM for Long Term Time Series Forecasting | None |
24-10-22|[xLSTM-Mixer](https://arxiv.org/abs/2410.16928)|  |Arxiv 2024| xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories | [xlstm-mixer](https://github.com/mauricekraus/xlstm-mixer) |
MLP.
Date | Method |Type| Conference | Paper Title and Paper Interpretation (In Chinese) | Code |
| -------- | --------------------------------------------- |-----| ---------- | ------------------------------------------------------------ | ---------------------------------------------- |
| 19-05-24 | [NBeats](https://arxiv.org/abs/1905.10437)🌟 |  | ICLR 2020 | [N-BEATS: Neural Basis Expansion Analysis For Interpretable Time Series Forecasting](https://zhuanlan.zhihu.com/p/572850227) | [NBeats](https://github.com/philipperemy/n-beats) |
| 21-04-12 | [NBeatsX](https://arxiv.org/abs/2104.05522)| | IJoF 2022 | [Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx](https://zhuanlan.zhihu.com/p/572955881) | [NBeatsX](https://github.com/cchallu/nbeatsx) |
| 22-01-30 | [N-HiTS](https://arxiv.org/abs/2201.12886)🌟 |  | AAAI 2023 | [N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting](https://zhuanlan.zhihu.com/p/573203887) | [N-HiTS](https://github.com/cchallu/n-hits) |
| 22-05-15 | [DEPTS](https://arxiv.org/abs/2203.07681) |  | ICLR 2022 | [DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting](https://zhuanlan.zhihu.com/p/572984932) | [DEPTS](https://github.com/weifantt/depts) |
| 22-05-24 | [FreDo](https://arxiv.org/abs/2205.12301)|  |Arxiv 2022|FreDo: Frequency Domain-based Long-Term Time Series Forecasting| None |
| 22-05-26 | [DLinear](https://arxiv.org/abs/2205.13504)🌟 |  | AAAI 2023 | [Are Transformers Effective for Time Series Forecasting?](https://zhuanlan.zhihu.com/p/569194246) | [DLinear](https://github.com/cure-lab/DLinear) |
| 22-06-24 | [TreeDRNet](https://arxiv.org/abs/2206.12106)|  | Arxiv 2022 | TreeDRNet: A Robust Deep Model for Long Term Time Series Forecasting | None |
| 22-07-04 | [LightTS](https://arxiv.org/abs/2207.01186) |  | Arxiv 2022 | Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures | [LightTS](https://tinyurl.com/5993cmus) |
| 22-08-10 | [STID](https://arxiv.org/abs/2208.05233) |  | CIKM 2022 | Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting | [STID](https://github.com/zezhishao/stid) |
| 23-01-30 | [SimST](https://arxiv.org/abs/2301.12603) |  | Arxiv 2023 | Do We Really Need Graph Neural Networks for Traffic Forecasting? | None |
| 23-02-09 | [MTS-Mixers](https://arxiv.org/abs/2302.04501)|  | Arxiv 2023 | MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing | [MTS-Mixers](https://github.com/plumprc/MTS-Mixers) |
| 23-03-10 | [TSMixer](https://arxiv.org/abs/2303.06053)|  | Arxiv 2023 | TSMixer: An all-MLP Architecture for Time Series Forecasting | None |
| 23-04-17 | [TiDE](https://arxiv.org/abs/2304.08424)🌟 |  | Arxiv 2023 | [Long-term Forecasting with TiDE: Time-series Dense Encoder](https://zhuanlan.zhihu.com/p/624828590) | [TiDE](https://zhuanlan.zhihu.com/p/624828590) |
| 23-05-18 | [RTSF](https://arxiv.org/abs/2305.10721) |  | Arxiv 2023 | Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping | [RTSF](https://github.com/plumprc/rtsf) |
| 23-05-30 | [Koopa](https://arxiv.org/abs/2305.18803)🌟 |  | NIPS 2023 | [Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors](https://zhuanlan.zhihu.com/p/635356173) | [Koopa](https://github.com/thuml/Koopa) |
| 23-06-14 | [CI-TSMixer](https://arxiv.org/abs/2306.09364) |  | KDD 2023 | TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting | None |
| 23-07-06 | [FITS](https://arxiv.org/abs/2307.03756)🌟 |  | ICLR 2024 | [FITS: Modeling Time Series with 10k Parameters](https://zhuanlan.zhihu.com/p/669221150) | [FITS](https://anonymous.4open.science/r/FITS) |
| 23-08-14 | [ST-MLP](https://arxiv.org/abs/2308.07496) |  | Arxiv 2023 | ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecasting | None |
| 23-08-25 | [TFDNet](https://arxiv.org/abs/2308.13386) |  | Arxiv 2023 | TFDNet: Time-Frequency Enhanced Decomposed Network for Long-term Time Series Forecasting | None |
| 23-11-10 | [FreTS](https://arxiv.org/abs/2311.06184) |  | NIPS 2023 | Frequency-domain MLPs are More Effective Learners in Time Series Forecasting | [FreTS](https://github.com/aikunyi/FreTS)
| 23-12-11 | [MoLE](https://arxiv.org/abs/2312.06786) |  | AISTATS 2024 | Mixture-of-Linear-Experts for Long-term Time Series Forecasting | [MoLE](https://github.com/RogerNi/MoLE) |
| 23-12-22 | [STL](https://arxiv.org/abs/2312.14869) |  | Arxiv 2023 | Spatiotemporal-Linear: Towards Universal Multivariate Time Series Forecasting | None |
| 24-01-04 | [U-Mixer](https://arxiv.org/abs/2401.02236) |  | AAAI 2024 | U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting | None |
| 24-01-16 | [TimeMixer](https://openreview.net/forum?id=7oLshfEIC2) |  | ICLR 2024 | [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://zhuanlan.zhihu.com/p/686772622) | [TimeMixer](https://github.com/kwuking/TimeMixer) |
| 24-02-16 | [RPMixer](https://arxiv.org/abs/2402.10487) |  | Arxiv 2024 | Random Projection Layers for Multidimensional Time Sires Forecasting | None |
| 24-02-20 | [IDEA](https://arxiv.org/abs/2402.12767) |  | Arxiv 2024 | When and How: Learning Identifiable Latent States for Nonstationary Time Series Forecasting | None |
| 24-03-04 | [CATS](https://arxiv.org/abs/2403.01673) |  | ICML 2024 | CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables | None |
| 24-03-21 | [OLS](https://arxiv.org/abs/2403.14587) |  | ICML 2024 | An Analysis of Linear Time Series Forecasting Models | None |
| 24-03-24 | [HDMixer](https://ojs.aaai.org/index.php/AAAI/article/view/29155) |  | AAAI 2024 | HDMixer: Hierarchical Dependency with Extendable Patch for Multivariate Time Series Forecasting | [HDMixer](https://github.com/hqh0728/HDMixer) |
| 24-04-22 | [SOFTS](https://arxiv.org/abs/2404.14197) |  | NIPS 2024 | SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion | [SOFTS](https://github.com/secilia-cxy/softs) |
| 24-05-02 | [SparseTSF](https://arxiv.org/abs/2405.00946) |  | ICML 2024 | [SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters](https://zhuanlan.zhihu.com/p/701070533) | [SparseTSF](https://github.com/lss-1138/SparseTSF) |
| 24-05-10 | [TEFN](https://arxiv.org/abs/2405.06419) |  | Arxiv 2024 | Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting | [TEFN](https://github.com/ztxtech/Time-Evidence-Fusion-Network) |
| 24-05-22 | [PDMLP](https://arxiv.org/abs/2405.13575) |  | Arxiv 2024 | PDMLP: Patch-based Decomposed MLP for Long-Term Time Series Forecasting | None |
| 24-06-06 | [AMD](https://arxiv.org/abs/2406.03751) |  | Arxiv 2024 | Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting | [AMD](https://github.com/TROUBADOUR000/AMD) |
| 24-06-07 | [TimeSieve](https://arxiv.org/abs/2406.05036) |  | Arxiv 2024 | TimeSieve: Extracting Temporal Dynamics through Information Bottlenecks | [TimeSieve](https://github.com/xll0328/TimeSieve) |
| 24-06-29 | [DERITS](https://arxiv.org/abs/2407.00502) |  | IJCAI 2024 | Deep Frequency Derivative Learning for Non-stationary Time Series Forecasting | None |
| 24-07-15 | [ODFL](https://arxiv.org/abs/2407.10419) |  | Arxiv 2024 | Omni-Dimensional Frequency Learner for General Time Series Analysis | None |
| 24-07-17 | [FreDF](https://arxiv.org/abs/2407.12415) |  | MM 2024 | Not All Frequencies Are Created Equal: Towards a Dynamic Fusion of Frequencies in Time-Series Forecasting | None |
| 24-09-26 | [PGN](https://arxiv.org/abs/2409.17703) |  | NIPS 2024 | PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting | [TPGN](https://github.com/Water2sea/TPGN) |
| 24-09-27 | [CycleNet](https://arxiv.org/abs/2409.18479) |  | NIPS 2024 | [CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns](https://zhuanlan.zhihu.com/p/778345073) | [CycleNet](https://github.com/ACAT-SCUT/CycleNet) |
| 24-10-02 | [MMFNet](https://arxiv.org/abs/2410.02070) |  | Arxiv 2024 | MMFNet: Multi-Scale Frequency Masking Neural Network for Multivariate Time Series Forecasting | None |
| 24-10-02 | [MixLinear](https://arxiv.org/abs/2410.02081) |  | Arxiv 2024 | MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with 0.1K Parameters | None |
| 24-10-07 | [NFM](https://arxiv.org/abs/2410.04703) |  | Arxiv 2024 | Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis | [NFM](https://github.com/minkiml/NFM) |
| 24-10-13 | [TFPS](https://arxiv.org/abs/2410.09836) |  | Arxiv 2024 | Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift | [TFPS](https://github.com/syrGitHub/TFPS) |
| 24-10-21 | [LTBoost](https://dl.acm.org/doi/pdf/10.1145/3627673.3679527) |  | CIKM 2024 | LTBoost: Boosted Hybrids of Ensemble Linear and Gradient Algorithms for the Long-term Time Series Forecasting | [LTBoost](https://github.com/hubtru/LTBoost) |
| 24-10-22 | [LiNo](https://arxiv.org/abs/2410.17159) |  | Arxiv 2024 | LiNo: Advancing Recursive Residual Decomposition of Linear and Nonlinear Patterns for Robust Time Series Forecasting | [LiNo](https://github.com/Levi-Ackman/LiNo) |
| 24-11-03 | [FilterNet](https://arxiv.org/abs/2411.01623) |  | NIPS 2024 | FilterNet: Harnessing Frequency Filters for Time Series Forecasting | [FilterNet](https://github.com/aikunyi/FilterNet) |
| 24-11-26 | [DiPE-Linear](https://arxiv.org/abs/2411.17257) |  | Arxiv 2024 | Disentangled Interpretable Representation for Efficient Long-term Time Series Forecasting | [DiPE-Linear](https://github.com/wintertee/DiPE-Linear) |
| 24-12-02 | [FSMLP](https://arxiv.org/abs/2412.01654) |  | Arxiv 2024 | FSMLP: Modelling Channel Dependencies With Simplex Theory Based Multi-Layer Perceptions In Frequency Domain | [FSMLP](https://github.com/fmlyd/fsmlp) |
| 24-12-09 | [LMS-AutoTSF](https://arxiv.org/abs/2412.06866) |  | Arxiv 2024 | LMS-AutoTSF: Learnable Multi-Scale Decomposition and Integrated Autocorrelation for Time Series Forecasting | [LMS-TSF](https://github.com/mribrahim/LMS-TSF) |
| 24-12-14 | [DUET](https://arxiv.org/abs/2412.10859)🔥 |  | KDD 2025 | DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting | [DUET](https://github.com/decisionintelligence/duet) |
| 24-12-18 | [PreMixer](https://arxiv.org/abs/2412.13607) |  | Arxiv 2024 | PreMixer: MLP-Based Pre-training Enhanced MLP-Mixers for Large-scale Traffic Forecasting | None |
| 24-12-22 | [WPMixer](https://arxiv.org/abs/2412.17176) |  | AAAI 2025 | WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecasting | None |
| 24-12-30 | [AverageLinear](https://arxiv.org/abs/2412.20727) |  | Arxiv 2024 | AverageLinear: Enhance Long-Term Time series forcasting with simple averaging | None |
| 25-01-25 | [FreqMoE](https://arxiv.org/abs/2501.15125) |  | AISTATS 2025 | FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts | [FreqMoE](https://github.com/sunbus100/FreqMoE-main) |
| 25-01-27 | [SWIFT](https://arxiv.org/abs/2501.16178) |  | Arxiv 2025 | SWIFT: Mapping Sub-series with Wavelet Decomposition Improves Time Series Forecasting | [swift](https://github.com/lancelotxwx/swift) |
| 25-01-28 | [Amplifier](https://arxiv.org/abs/2501.17216) |  | AAAI 2025 | Amplifier: Bringing Attention to Neglected Low-Energy Components in Time Series Forecasting | [amplifier](https://github.com/aikunyi/amplifier) |
| 25-01-31 | [BEAT](https://arxiv.org/abs/2501.19065) |  | Arxiv 2025 | BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting | None |
| 25-02-05 | [MTLinear](https://arxiv.org/abs/2502.03571) |  | AISTATS 2025 | A Multi-Task Learning Approach to Linear Multivariate Forecasting | [MTLinear](https://github.com/azencot-group/MTLinear) |
| 25-02-08 | [TSAA](https://arxiv.org/abs/2405.00319) |  | TMLR | Data Augmentation Policy Search for Long-Term Forecasting | [TSAA](https://github.com/azencot-group/TSAA) |
| 25-02-14 | [HADL](https://arxiv.org/abs/2502.10569) |  | Arxiv 2025 | HADL Framework for Noise Resilient Long-Term Time Series Forecasting | [HADL](https://github.com/forgee-master/HADL) |
| 25-02-17 | [IMTS-Mixer](https://arxiv.org/abs/2502.11816) |  | Arxiv 2025 | IMTS-Mixer: Mixer-Networks for Irregular Multivariate Time Series Forecasting | [IMTS-Mixer](https://anonymous.4open.science/r/IMTS-Mixer-D63C/) |
| 25-02-20 | [TimeDistill](https://arxiv.org/abs/2502.15016) |  | Arxiv 2025 | TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation | None |
| 25-02-24 | [ReFocus](https://arxiv.org/abs/2502.16890) |  | Arxiv 2025 | ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting | [refocus](https://github.com/levi-ackman/refocus) |
| 25-02-27 | [FIA-Net](https://arxiv.org/abs/2502.19983) |  | Arxiv 2025 | Efficient Time Series Forecasting via Hyper-Complex Models and Frequency Aggregation | [FIA-Net](https://anonymous.4open.science/r/research-1803/) |
| 25-02-28 | [UltraSTF](https://arxiv.org/abs/2502.20634) |  | Arxiv 2025 | A Compact Model for Large-Scale Time Series Forecasting | None |
| 25-03-04 | [CDFM](https://arxiv.org/abs/2503.02609) |  | Arxiv 2025 | Lightweight Channel-wise Dynamic Fusion Model: Non-stationary Time Series Forecasting via Entropy Analysis | None |
| 25-03-30 | [SFNN](https://arxiv.org/abs/2503.23621) |  | Arxiv 2025 | Simple Feedfoward Neural Networks are Almost All You Need for Time Series Forecasting | None |
| 25-04-02 | [DRAN](https://arxiv.org/abs/2504.01531) |  | Arxiv 2025 | DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting | None |
| 25-04-11 | [FilterTS](https://doi.org/10.1609/aaai.v39i20.35438) |  | AAAI 2025 | FilterTS: Comprehensive Frequency Filtering for Multivariate Time Series Forecasting | [FilterTS](https://github.com/wyl010607/FilterTS) |
| 25-05-01 | [AiT](https://arxiv.org/abs/2505.00590) |  | Arxiv 2025 | Unlocking the Potential of Linear Networks for Irregular Multivariate Time Series Forecasting | None |
| 25-05-07 | [RAFT](https://arxiv.org/abs/2505.04163) |  | ICML 2025 | Retrieval Augmented Time Series Forecasting | [RAFT](https://github.com/archon159/RAFT) |
| 25-05-12 | [OLinear](https://arxiv.org/abs/2505.08550) |  | Arxiv 2025 | OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain | [OLinear](https://anonymous.4open.science/r/OLinear) |
| 25-05-13 | [MDMixer](https://arxiv.org/abs/2505.08199) |  | Arxiv 2025 | A Multi-scale Representation Learning Framework for Long-Term Time Series Forecasting | None |
| 25-05-15 | [ALinear](https://arxiv.org/abs/2505.10172) |  | Arxiv 2025 | Does Scaling Law Apply in Time Series Forecasting? | None |
| 25-05-16 | [APN](https://arxiv.org/abs/2505.11250) |  | Arxiv 2025 | Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline | None |
| 25-05-17 | [WaveTS](https://arxiv.org/abs/2505.11781) |  | Arxiv 2025 | Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting | None |
| 25-05-20 | [CRAFT](https://arxiv.org/abs/2505.13896) |  | Arxiv 2025 | CRAFT: Time Series Forecasting with Cross-Future Behavior Awareness | [CRAFT](https://github.com/CRAFTinTSF/CRAFT) |
| 25-05-25 | [CMoS](https://arxiv.org/abs/2505.19090) |  | ICML 2025 | CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations | [CMoS](https://github.com/cstcloudops/cmos) |
| 25-05-29 | [CrossLinear](https://arxiv.org/abs/2505.23116) |  | KDD 2025 | CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables | [CrossLinear](https://github.com/mumiao2000/CrossLinear) |
TCN/CNN.
Date|Method|Type|Conference|Paper Title and Paper Interpretation (In Chinese)|Code
-----|----|----|-----|-----|-----
| 19-05-09 | [DeepGLO](https://arxiv.org/abs/1905.03806)🌟 |  | NIPS 2019 | Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting| [deepglo](https://github.com/rajatsen91/deepglo) |
| 19-05-22 | [DSANet](https://dl.acm.org/doi/abs/10.1145/3357384.3358132) |  | CIKM 2019 | DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting | [DSANet](https://github.com/bighuang624/DSANet) |
| 19-12-11 | [MLCNN](https://arxiv.org/abs/1912.05122) |  | AAAI 2020 | Towards Better Forecasting by Fusing Near and Distant Future Visions | [MLCNN](https://github.com/smallGum/MLCNN-Multivariate-Time-Series) |
| 21-06-17 | [SCINet](https://arxiv.org/abs/2106.09305) |  | NIPS 2022 | [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mp.weixin.qq.com/s/mHleT4EunD82hmEfHnhkig) | [SCINet](https://github.com/cure-lab/SCINet) |
| 22-09-22 | [MICN](https://openreview.net/forum?id=zt53IDUR1U) |  | ICLR 2023 | [MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting](https://zhuanlan.zhihu.com/p/603468264) | [MICN](https://github.com/whq13018258357/MICN) |
| 22-09-22 | [TimesNet](https://arxiv.org/abs/2210.02186)🌟 |  | ICLR 2023 | [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://zhuanlan.zhihu.com/p/604100426) | [TimesNet](https://github.com/thuml/TimesNet) |
| 23-02-23 | [LightCTS](https://arxiv.org/abs/2302.11974) |  | SIGMOD 2023 | LightCTS: A Lightweight Framework for Correlated Time Series Forecasting | [LightCTS](https://github.com/ai4cts/lightcts) |
| 23-05-25 | [TLNets](https://arxiv.org/abs/2305.15770) |  | Arxiv 2023 | TLNets: Transformation Learning Networks for long-range time-series prediction | [TLNets](https://github.com/anonymity111222/tlnets) |
| 23-06-04 | [Cross-LKTCN](https://arxiv.org/abs/2306.02326) |  | Arxiv 2023 | Cross-LKTCN: Modern Convolution Utilizing Cross-Variable Dependency for Multivariate Time Series Forecasting Dependency for Multivariate Time Series Forecasting | None |
| 23-06-12 | [MPPN](https://arxiv.org/abs/2306.06895) |  | Arxiv 2023 | MPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting | None |
| 23-06-19 | [FDNet](https://arxiv.org/abs/2306.10703) |  | KBS 2023 | FDNet: Focal Decomposed Network for Efficient, Robust and Practical Time Series Forecasting | [FDNet](https://github.com/OrigamiSL/FDNet-KBS-2023) |
| 23-10-01 | [PatchMixer](https://browse.arxiv.org/abs/2310.00655) |  | Arxiv 2023 | PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting | [PatchMixer](https://github.com/Zeying-Gong/PatchMixer) |
| 23-11-01 | [WinNet](https://arxiv.org/abs/2311.00214) |  | Arxiv 2023 | WinNet:time series forecasting with a window-enhanced period extracting and interacting | None |
| 23-11-27 | [ModernTCN](https://openreview.net/forum?id=vpJMJerXHU)🌟 |  | ICLR 2024 | [ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis](https://zhuanlan.zhihu.com/p/668946041) | [ModernTCN](https://github.com/luodhhh/ModernTCN) |
| 23-11-27 | [UniRepLKNet](https://arxiv.org/abs/2311.15599) |  | Arxiv 2023 | UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition | [UniRepLKNet](https://github.com/ailab-cvc/unireplknet) |
| 24-03-03 | [ConvTimeNet](https://arxiv.org/abs/2403.01493) |  | WWW 2025 | ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis | [ConvTimeNet](https://github.com/Mingyue-Cheng/ConvTimeNet) |
| 24-05-20 | [ATVCNet](https://arxiv.org/abs/2405.12038) |  | Arxiv 2024| ATVCNet: Adaptive Extraction Network for Multivariate Long Sequence Time-Series Forecasting | None |
| 24-05-24 | [FTMixer](https://arxiv.org/abs/2405.15256) |  | Arxiv 2024| FTMixer: Frequency and Time Domain Representations Fusion for Time Series Modeling | [FTMixer](https://github.com/FMLYD/FTMixer) |
| 24-10-07 | [TimeCNN](https://arxiv.org/abs/2410.04853) |  | Arxiv 2024| TimeCNN: Refining Cross-Variable Interaction on Time Point for Time Series Forecasting | None |
| 24-10-21 | [TimeMixer++](https://arxiv.org/abs/2410.16032) |  | ICLR 2025| [TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis](https://zhuanlan.zhihu.com/p/12926871013) | None |
| 24-11-07 | [EffiCANet](https://arxiv.org/abs/2411.04669) |  | Arxiv 2024| EffiCANet: Efficient Time Series Forecasting with Convolutional Attention | None |
| 24-12-23 | [xPatch](https://arxiv.org/abs/2412.17323) |  | AAAI 2025 | xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition | [xPatch](https://github.com/stitsyuk/xpatch) |
| 25-01-23 | [TVNet](https://openreview.net/forum?id=MZDdTzN6Cy) |  | ICLR 2025 | TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation | None |
GNN.
Date | Method | Type | Conference | Paper Title and Paper Interpretation (In Chinese) | Code |
| ---- | ------ | ------ | ---------- | ------------------------------------------------- | ---- |
| 17-09-14 | [STGCN](https://arxiv.org/abs/1709.04875)🌟🔥 |  | IJCAI 2018 | Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting | [STGCN](https://github.com/VeritasYin/STGCN_IJCAI-18) |
| 19-05-31 | [Graph WaveNet](https://arxiv.org/abs/1906.00121)🔥 |  | IJCAI 2019 | Graph WaveNet for Deep Spatial-Temporal Graph Modeling | [Graph-WaveNet](https://github.com/nnzhan/Graph-WaveNet) |
| 19-07-17 | [ASTGCN](https://ojs.aaai.org/index.php/AAAI/article/view/3881)🔥 |  | AAAI 2019 | Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting | [ASTGCN](https://github.com/guoshnBJTU/ASTGCN-r-pytorch) |
| 20-04-03 | [SLCNN](https://ojs.aaai.org/index.php/AAAI/article/view/5470)🔥 |  | AAAI 2020 | Spatio-Temporal Graph Structure Learning for Traffic Forecasting | None |
| 20-04-03 | [GMAN](https://ojs.aaai.org/index.php/AAAI/article/view/5477)🔥 |  | AAAI 2020 | GMAN: A Graph Multi-Attention Network for Traffic Prediction | [GMAN](https://github.com/zhengchuanpan/GMAN) |
| 20-05-03 | [MTGNN](https://arxiv.org/abs/2005.01165)🌟🔥 |  | KDD 2020 | Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks | [MTGNN](https://github.com/nnzhan/MTGNN) |
| 20-09-26 | [AGCRN](https://proceedings.neurips.cc/paper_files/paper/2020/file/ce1aad92b939420fc17005e5461e6f48-Paper.pdf)🌟🔥 |  | NIPS 2020 | Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting | [AGCRN](https://github.com/LeiBAI/AGCRN) |
| 21-03-13 | [StemGNN](https://arxiv.org/abs/2103.07719)🌟🔥 |  | NIPS 2020 | Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting | [StemGNN](https://github.com/microsoft/StemGNN) |
| 22-05-16 | [TPGNN](https://openreview.net/forum?id=pMumil2EJh) |  | NIPS 2022 | Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks | [TPGNN](https://github.com/zyplanet/TPGNN) |
| 22-06-18 | [D2STGNN](https://arxiv.org/abs/2206.09112) |  | VLDB 2022 | Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting | [D2STGNN](https://github.com/zezhishao/d2stgnn) |
| 23-05-12 | [DDGCRN](https://www.sciencedirect.com/science/article/abs/pii/S0031320323003710?via%3Dihub) |  | PR 2023 | A Decomposition Dynamic graph convolutional recurrent network for traffic forecasting | [DDGCRN](https://github.com/wengwenchao123/DDGCRN) |
| 23-05-30 | [HiGP](https://arxiv.org/abs/2305.19183) |  | ICML 2024 | Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting | None |
| 23-07-10 | [NexuSQN](https://arxiv.org/abs/2307.01482) |  | Arxiv 2023 | Nexus sine qua non: Essentially connected neural networks for spatial-temporal forecasting of multivariate time series | None |
| 23-11-10 | [FourierGNN](https://arxiv.org/abs/2311.06190) |  | NIPS 2023 | FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective | [FourierGNN](https://github.com/aikunyi/FourierGNN) |
| 23-12-05 | [SAMSGL](https://arxiv.org/abs/2312.02646) |  | TETCI 2023 | SAMSGL: Series-Aligned Multi-Scale Graph Learning for Spatio-Temporal Forecasting | None |
| 23-12-27 | [TGCRN](https://arxiv.org/abs/2312.16403) |  | ICDE 2024 | Learning Time-aware Graph Structures for Spatially Correlated Time Series Forecasting | None |
| 23-12-27 | [FCDNet](https://arxiv.org/abs/2312.16450) |  | Arxiv 2023 | FCDNet: Frequency-Guided Complementary Dependency Modeling for Multivariate Time-Series Forecasting | [FCDNet](https://github.com/oncecwj/fcdnet) |
| 23-12-31 | [MSGNet](https://arxiv.org/abs/2401.00423) |  | AAAI 2024 | MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting | [MSGNet](https://github.com/YoZhibo/MSGNet) |
| 24-01-15 | [RGDAN](https://www.sciencedirect.com/science/article/abs/pii/S0893608023007542?via%3Dihub) |  | NN 2024 | RGDAN: A random graph diffusion attention network for traffic prediction | [RGDAN](https://github.com/wengwenchao123/RGDAN) |
| 24-01-16 | [BiTGraph](https://openreview.net/forum?id=O9nZCwdGcG) |  | ICLR 2024 | Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values | [BiTGraph](https://github.com/chenxiaodanhit/BiTGraph) |
| 24-01-24 | [TMP](https://arxiv.org/abs/2401.13157) |  | AAAI 2024 | Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence | None |
| 24-02-16 | [HD-TTS](https://arxiv.org/abs/2402.10634) |  | ICML 2024 | Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling | [hdtts](https://github.com/marshka/hdtts) |
| 24-05-02 | [T-PATCHGNN](https://openreview.net/forum?id=UZlMXUGI6e) |  | ICML 2024 | Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach | [t-PatchGNN](https://github.com/usail-hkust/t-PatchGNN) |
| 24-05-17 | [HimNet](https://arxiv.org/abs/2405.10800) |  | KDD 2024 | Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting | [HimNet](https://github.com/XDZhelheim/HimNet) |
| 24-05-28 | [GFC-GNN](https://arxiv.org/abs/2405.18036) |  | Arxiv 2024 | ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks | None |
| 24-06-18 | [SAGDFN](https://arxiv.org/abs/2406.12282) |  | ICDE 2024 | SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting | None |
| 24-10-17 | [GNeuralFlow](https://arxiv.org/abs/2410.14030) |  | NIPS 2024 | Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series | [GNeuralFlow](https://github.com/gmerca/GNeuralFlow) |
| 24-10-24 | [TEAM](https://arxiv.org/abs/2410.19192) |  | VLDB 2025 | TEAM: Topological Evolution-aware Framework for Traffic Forecasting | [TEAM](https://github.com/kv