Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ztxtech/Time-Evidence-Fusion-Network
Official implementation of "Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting" (https://arxiv.org/abs/2405.06419)
https://github.com/ztxtech/Time-Evidence-Fusion-Network
cuda deep-learning machine-learning macos neural-network neural-networks pytorch time-series time-series-analysis time-series-forecasting time-series-prediction uestc
Last synced: 3 months ago
JSON representation
Official implementation of "Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting" (https://arxiv.org/abs/2405.06419)
- Host: GitHub
- URL: https://github.com/ztxtech/Time-Evidence-Fusion-Network
- Owner: ztxtech
- License: mit
- Created: 2024-04-22T13:48:06.000Z (9 months ago)
- Default Branch: master
- Last Pushed: 2024-10-21T10:52:32.000Z (3 months ago)
- Last Synced: 2024-10-23T09:27:56.773Z (3 months ago)
- Topics: cuda, deep-learning, machine-learning, macos, neural-network, neural-networks, pytorch, time-series, time-series-analysis, time-series-forecasting, time-series-prediction, uestc
- Language: Python
- Homepage: https://ztxtech.github.io/Time-Evidence-Fusion-Network/
- Size: 3.51 MB
- Stars: 62
- Watchers: 2
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-time-series - [code
README
Time Evidence Fusion Network (TEFN):
Multi-source View in Long-Term Time Series Forecasting
**Repo Status:**
[](https://github.com/ztxtech/Time-Evidence-Fusion-Network)
[](https://github.com/ztxtech/Time-Evidence-Fusion-Network/activity?ref=master&activity_type=direct_push)
[](https://github.com/ztxtech/Time-Evidence-Fusion-Network/graphs/commit-activity)
[](https://github.com/ztxtech/Time-Evidence-Fusion-Network)
[](https://github.com/ztxtech/Time-Evidence-Fusion-Network)
[](https://github.com/ztxtech/Time-Evidence-Fusion-Network)
[](https://github.com/ztxtech/Time-Evidence-Fusion-Network)
**Implementation:**
[](https://arxiv.org/abs/2405.06419)
[](https://www.python.org/)
[](https://pytorch.org/)
[](https://pytorch.org/docs/2.1/cuda.html)
[](https://pytorch.org/docs/2.1/mps.html)
## Updates
🚩 **News** (2024.05.14) Compatible with MPS backend, TEFN can be trained by [](https://support.apple.com/zh-cn/111883).
## Overview
This is the official code implementation project for paper **"Time Evidence Fusion Network: Multi-source View in
Long-Term Time Series Forecasting"**. The code implementation refers
to [](https://github.com/thuml/Time-Series-Library).
Thanks very much
for [](https://github.com/thuml/Time-Series-Library)'s contribution to this project.
The **Time Evidence Fusion Network (TEFN)** is a groundbreaking deep learning model designed for long-term time series
forecasting. It integrates the principles of information fusion and evidence theory to achieve superior performance in
real-world applications where timely predictions are crucial. TEFN introduces the Basic Probability Assignment (BPA)
Module, leveraging fuzzy theory, and the Time Evidence Fusion Network to enhance prediction accuracy, stability, and
interpretability.
## Key Features
- **Information Fusion Perspective**: TEFN addresses time series forecasting from a unique angle, focusing on the fusion
of multi-source information to boost prediction accuracy.
- **BPA Module**: At its core, TEFN incorporates a BPA Module that maps diverse information sources to probability
distributions related to the target outcome. This module exploits the interpretability of evidence theory, using fuzzy
membership functions to represent uncertainty in predictions.
- **Interpretability**: Due to its roots in fuzzy logic, TEFN provides clear insights into the decision-making process,
enhancing model explainability.
- **State-of-the-Art Performance**: TEFN demonstrates competitive results, with prediction errors comparable to leading
models like PatchTST, while maintaining high efficiency and requiring fewer parameters than complex models such as
Dlinear.
- **Robustness and Stability**: The model showcases resilience to hyperparameter tuning, exhibiting minimal fluctuations
even under random selections, ensuring consistent performance across various settings.
- **Efficiency**: With optimized training times and a compact model footprint, TEFN is particularly suitable for
resource-constrained environments.
## Getting Started
### Requirements
-  Python >= 3.6
-  PyTorch >= 1.7.0
-  Other dependencies listed
in `requirements.txt`
### Installation
Clone the repository:
```bash
git clone https://github.com/ztxtech/Time-Evidence-Fusion-Network.git
cd Time-Evidence-Fusion-Network
pip install -r requirements.txt
```
### Usage
#### Download Dataset
You can obtain datasets
from [](https://drive.google.com/drive/folders/13Cg1KYOlzM5C7K8gK8NfC-F3EYxkM3D2?usp=sharing)
or [](https://pan.baidu.com/s/1r3KhGd0Q9PJIUZdfEYoymg?pwd=i9iy),
Then place the downloaded data in the folder`./dataset`.
#### Load Config
1. Modify the specific configuration file in `./run_config.py`.
```python
config_path = '{your chosen config file path}'
```
2. Run `./run_config.py` directly.
```bash
python run_config.py
```
#### Switching Running Devices
1. Find required configuration file `*.json` in `./configs`.
2. Modify `*.json` file.
```
{
# ...
# Nvidia CUDA Device {0}
# 'gpu': 0
# Apple MPS Device
# 'gpu': 'mps'
# ...
}
```
#### Other Operations
Other related operations refer
to [](https://github.com/thuml/Time-Series-Library).
#### Citation
If you find TEFN useful in your research, please cite our work as per the citation.
```bibtex
@misc{TEFN,
title={Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting},
author={Tianxiang Zhan and Yuanpeng He and Zhen Li and Yong Deng},
year={2024},
journal={arXiv}
}
```
## Acknowledgement
We appreciate the following GitHub repos a lot for their valuable code and efforts.
- [Time Series Library ](https://github.com/thuml/Time-Series-Library)'
- [TSFpaper ](https://github.com/ddz16/TSFpaper)
- [Time-Series-Forecasting-and-Deep-Learning ](https://github.com/DaoSword/Time-Series-Forecasting-and-Deep-Learning)
- [awesome-opensource ](https://github.com/gitroomhq/awesome-opensource)
### From [Time Series Library](https://github.com/thuml/Time-Series-Library)
This library is constructed based on the following repos:
- Forecasting: https://github.com/thuml/Autoformer.
All the experiment datasets are public, and we obtain them from the following links:
- Long-term Forecasting and Imputation: https://github.com/thuml/Autoformer.
- Short-term Forecasting: https://github.com/ServiceNow/N-BEATS.
## Contact
If you have any questions or suggestions, feel free to contact:
- (**Primary**) Tianxiang Zhan [([email protected])](mailto:[email protected])
[](mailto:[email protected])
[](https://scholar.google.com.hk/citations?user=bRYz250AAAAJ)
[](https://www.researchgate.net/profile/Tianxiang-Zhan)
- Yuanpeng He [([email protected])](mailto:[email protected])
[](mailto:[email protected])
[](https://scholar.google.com/citations?user=HaefBCQAAAAJ)
[](https://www.researchgate.net/profile/Yuanpeng-He)
Or describe it in Issues.
## Star History
[](https://star-history.com/#ztxtech/Time-Evidence-Fusion-Network&Date)