pathformer - GitLite

KO | EN

gitlite — search

#javascript #hacktoberfest #react #ai #rust #linux #nodejs #java #windows #kubernetes #vue #mcp #openai #open-source

pathformer

(★ 268)

No description available.

파일 탐색기

최종 버전 다운로드 (.zip)

- __init__.py
- data_factory.py
- data_loader.py
- exp_basic.py
- exp_main.py
- framework.png
- multi-scale transformer.png
- AMS.py
- Embedding.py
- Layer.py
- RevIN.py
- PathFormer.py
- - electricity.sh
  - ETTh1.sh
  - ETTh2.sh
  - ETTm1.sh
  - ETTm2.sh
  - traffic.sh
  - weather.sh
- decomposition.py
- masking.py
- metrics.py
- Other.py
- timefeatures.py
- tools.py
.gitignore
README.md
requirements.txt
run.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/decisionintelligence/pathformer

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd pathformer

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

## (ICLR 2024) Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

This code is a PyTorch implementation of our ICLR'24 paper "Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting". [[arXiv]](https://arxiv.org/abs/2402.05956)

🌟 Pathformer代码在阿里云仓库也进行同步更新：[阿里云Pathformer代码链接](https://github.com/alibaba/sreworks-ext/tree/main/aiops/Pathformer_ICLR2024)

## Citing Pathformer
If you find this resource helpful, please consider to cite our research:

```
@inproceedings{chen2024pathformer,
  author       = {Peng Chen and Yingying Zhang and Yunyao Cheng and Yang Shu and Yihang Wang and Qingsong Wen and Bin Yang and Chenjuan Guo},
  title        = {Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting},
  booktitle    = {International Conference on Learning Representations (ICLR)},
  year         = {2024}
}
```

## Introduction
 Pathformer, a Multi-Scale Transformer with Adaptive Pathways for time series forecasting. It integrates multi-scale temporal resolutions and temporal distances by introducing patch division with multiple patch sizes and dual attention on the divided patches, enabling the comprehensive modeling of multi-scale characteristics. Furthermore, adaptive pathways dynamically select and aggregate scale-specific characteristics based on the different temporal dynamics.

![The architecture of Pathformer](https://raw.githubusercontent.com/decisionintelligence/pathformer/main/figs/framework.png)

The important components of Pathformer: Multi-Scale Transformer Block and Multi-Scale Router.

![The structure of the Multi-Scale Transformer Block and Multi-Scale Router](https://raw.githubusercontent.com/decisionintelligence/pathformer/main/figs/multi-scale%20transformer.png)
## Requirements
To install all dependencies:
```
pip install -r requirements.txt
```

## Datasets
You can access the well pre-processed datasets from [Google Drive](https://drive.google.com/file/d/1NF7VEefXCmXuWNbnNe858WvQAkJ_7wuP/view), then place the downloaded contents under ./dataset
## Quick Demos
1. Download datasets and place them under ./dataset
2. Run each script in scripts/, for example
```
bash scripts/multivariate/ETTm2.sh
```

## Further Reading
1, [**Transformers in Time Series: A Survey**](https://arxiv.org/abs/2202.07125), in IJCAI 2023.
[\[GitHub Repo\]](https://github.com/qingsongedu/time-series-transformers-review)

```bibtex
@inproceedings{wen2023transformers,
  title={Transformers in time series: A survey},
  author={Wen, Qingsong and Zhou, Tian and Zhang, Chaoli and Chen, Weiqi and Ma, Ziqing and Yan, Junchi and Sun, Liang},
  booktitle={International Joint Conference on Artificial Intelligence(IJCAI)},
  year={2023}
}
```