{"id":20161910,"url":"https://github.com/zhangzw16/sageformer","last_synced_at":"2025-04-10T00:23:06.214Z","repository":{"id":223429404,"uuid":"760295165","full_name":"zhangzw16/SageFormer","owner":"zhangzw16","description":"Code for IoTJ 2024 paper \"SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting\".","archived":false,"fork":false,"pushed_at":"2024-03-29T10:18:51.000Z","size":62,"stargazers_count":58,"open_issues_count":0,"forks_count":4,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-24T02:06:42.865Z","etag":null,"topics":["deep-learning","time-series-forecasting"],"latest_commit_sha":null,"homepage":"https://ieeexplore.ieee.org/abstract/document/10423755","language":"Python","has_issues":false,"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/zhangzw16.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}},"created_at":"2024-02-20T06:34:02.000Z","updated_at":"2025-03-16T01:41:54.000Z","dependencies_parsed_at":"2024-03-01T09:29:53.971Z","dependency_job_id":"478feef3-74c3-4a5a-826d-f9648597e8f8","html_url":"https://github.com/zhangzw16/SageFormer","commit_stats":null,"previous_names":["zhangzw16/sageformer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhangzw16%2FSageFormer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhangzw16%2FSageFormer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhangzw16%2FSageFormer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhangzw16%2FSageFormer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zhangzw16","download_url":"https://codeload.github.com/zhangzw16/SageFormer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248132314,"owners_count":21053021,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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"}},"keywords":["deep-learning","time-series-forecasting"],"created_at":"2024-11-14T00:21:50.760Z","updated_at":"2025-04-10T00:23:06.177Z","avatar_url":"https://github.com/zhangzw16.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting\n\n![Visitors](https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fgithub.com%2Fzhangzw16%2FSageFormer\u0026label=VISITORS\u0026labelColor=%232ccce4\u0026countColor=%23697689)\n\nThis repository contains the code for the paper \"[SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting](https://ieeexplore.ieee.org/abstract/document/10423755)\" by Zhenwei Zhang, Linghang Meng, and Yuantao Gu, published in the IEEE Internet of Things Journal.\n\n## Introduction\n\nSageFormer is a novel series-aware graph-enhanced Transformer model designed for long-term forecasting of multivariate time-series (MTS) data. With the proliferation of IoT devices, MTS data has become ubiquitous, necessitating advanced models to forecast future behaviors. SageFormer addresses the challenge of capturing both intra- and inter-series dependencies, enhancing the predictive performance of Transformer-based models.\n\u003cdiv align=center\u003e\n\u003cimg width=\"1145\" alt=\"Screenshot 2024-02-20 at 14 56 56\" src=\"https://github.com/zhangzw16/SageFormer/assets/26004183/941c5e6d-d261-41fb-bf20-4211c4fa6d9e\"\u003e\n\u003cimg width=\"896\" alt=\"Screenshot 2024-02-20 at 14 58 19\" src=\"https://github.com/zhangzw16/SageFormer/assets/26004183/3ed21ee8-e11f-4da9-ad6d-c80413b33b07\"\u003e\n\u003c/div\u003e\n\n## Usage\nTo train and evaluate the SageFormer model:\n\n- Clone this repository\n- Download datasets from [Google Drive](https://drive.google.com/drive/folders/13Cg1KYOlzM5C7K8gK8NfC-F3EYxkM3D2) or [Baidu Drive](https://pan.baidu.com/share/init?surl=r3KhGd0Q9PJIUZdfEYoymg\u0026pwd=i9iy) and place them in the `./dataset` folder\n- Create a virtual environment and activate it\n- Install requirements `pip install -r requirements.txt`\n- Run scripts in the `./scripts` folder to train and evaluate the model, for example:\n    ```bash\n    sh scripts/long_term_forecast/ECL_script/SageFormer.sh\n    ``` \n- Model checkpoints and logs will be saved to outputs folder\n\n## Contacts\nFor any questions, please contact the authors at `zzw20 [at] mails.tsinghua.edu.cn` or write a [discussion on github](https://github.com/zhangzw16/SageFormer/discussions).\n\n## Citation\nIf you find this code or paper useful for your research, please cite:\n```bibtex\n@ARTICLE{zhang2024sageformer,\n  author={Zhang, Zhenwei and Meng, Linghang and Gu, Yuantao},\n  journal={IEEE Internet of Things Journal}, \n  title={SageFormer: Series-Aware Framework for Long-Term Multivariate Time Series Forecasting}, \n  year={2024},\n  doi={10.1109/JIOT.2024.3363451}}\n```\n\n# Acknowledgement\n\nThis library is constructed based on the following repos:\n- https://github.com/thuml/Time-Series-Library\n- https://github.com/PatchTST/PatchTST\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhangzw16%2Fsageformer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzhangzw16%2Fsageformer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhangzw16%2Fsageformer/lists"}