https://github.com/tsmotlp/fedrir
Pytorch Implementation of FedRIR: Rethinking Information Representation in Federated Learning (Accepted by WWW25, Oral)
https://github.com/tsmotlp/fedrir
Last synced: about 2 months ago
JSON representation
Pytorch Implementation of FedRIR: Rethinking Information Representation in Federated Learning (Accepted by WWW25, Oral)
- Host: GitHub
- URL: https://github.com/tsmotlp/fedrir
- Owner: tsmotlp
- Created: 2025-01-23T07:53:34.000Z (9 months ago)
- Default Branch: master
- Last Pushed: 2025-01-24T01:58:54.000Z (9 months ago)
- Last Synced: 2025-01-31T14:48:32.611Z (8 months ago)
- Language: Python
- Homepage:
- Size: 309 KB
- Stars: 0
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# FedRIR
This is the official PyTorch implementation of our WWW'25 **Oral** paper:
**FedRIR: Rethinking Information Representation in Federated Learning**
## Overview
## Requirements
- Python 3.x
- PyTorch
- torchvision
- numpy
## Datasets
We conduct experiments on six datasets:
- MNIST
- CIFAR-10
- CIFAR-100
- FashionMNIST
- OfficeCaltech10
- DomainNet
## Training
```
python main.py --dataset MNIST --num_clients 20 --global_epochs 1000 --join_ratio 1.0 --partition dir --alpha 0.1 --train_ratio 0.75
```
## Citation
If you find this code useful for your research, please cite our paper:
```
@inproceedings{huang2025fedrir,
title={FedRIR: Rethinking Information Representation in Federated Learning},
author={Huang, Yongqiang and Shao, Zerui and Yang, Ziyuan and Lu, Zexin and Zhang, Yi},
booktitle={Proceedings of the ACM on Web Conference 2025},
pages={807--816},
year={2025}
}
```
## License
This project is licensed under the MIT License.
## Contact
If you have any questions, please feel free to contact [yqhuang2912@gmail.com].