https://github.com/zhangzw16/sageformer

Code for IoTJ 2024 paper "SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting".
https://github.com/zhangzw16/sageformer

deep-learning time-series-forecasting

Last synced: 2 months ago
JSON representation

Code for IoTJ 2024 paper "SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting".

• Host: GitHub
• URL: https://github.com/zhangzw16/sageformer
• Owner: zhangzw16
• License: mit
• Created: 2024-02-20T06:34:02.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-03-29T10:18:51.000Z (10 months ago)
• Last Synced: 2024-03-29T11:32:02.938Z (10 months ago)
• Topics: deep-learning, time-series-forecasting
• Language: Python
• Homepage: https://ieeexplore.ieee.org/abstract/document/10423755
• Size: 60.5 KB
• Stars: 15
• Watchers: 3
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting

![Visitors](https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fgithub.com%2Fzhangzw16%2FSageFormer&label=VISITORS&labelColor=%232ccce4&countColor=%23697689)

This 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.

## Introduction

SageFormer 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.









## Usage

To train and evaluate the SageFormer model:

- Clone this repository

- Download datasets from [Google Drive](https://drive.google.com/drive/folders/13Cg1KYOlzM5C7K8gK8NfC-F3EYxkM3D2) or [Baidu Drive](https://pan.baidu.com/share/init?surl=r3KhGd0Q9PJIUZdfEYoymg&pwd=i9iy) and place them in the `./dataset` folder

- Create a virtual environment and activate it

- Install requirements `pip install -r requirements.txt`

- Run scripts in the `./scripts` folder to train and evaluate the model, for example:

    ```bash

    sh scripts/long_term_forecast/ECL_script/SageFormer.sh

    ``` 

- Model checkpoints and logs will be saved to outputs folder

## Contacts

For 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).

## Citation

If you find this code or paper useful for your research, please cite:

```bibtex

@ARTICLE{zhang2024sageformer,

  author={Zhang, Zhenwei and Meng, Linghang and Gu, Yuantao},

  journal={IEEE Internet of Things Journal}, 

  title={SageFormer: Series-Aware Framework for Long-Term Multivariate Time Series Forecasting}, 

  year={2024},

  doi={10.1109/JIOT.2024.3363451}}

```

# Acknowledgement

This library is constructed based on the following repos:

- https://github.com/thuml/Time-Series-Library

- https://github.com/PatchTST/PatchTST