This repository is the official Pytorch implementation DEMO of FedLSR framework in this paper: Towards Federated Learning against Noisy Labels via Local Self-Regularization (CIKM 2022 full paper track).
In this work, we provide a simple yet effective method FedLSR to tackle the distributed label noise issue when the total class number is not high. The slide for the oral presentation link is here. Meanwhile, we provide an implementation code to experiment on Clothing1M in this link. Note that, for experiments on clothing1M, it is suggested to raise the learning rate to 0.1 for FedLSR's implementation.
- FedAvg [paper]
- Symmetric Cross Entropy [paper] [code]
- Co-teaching [paper] [code]
- Robust Federated Learning [paper] [code]
- Python: 3.8
- Pytorch: 1.7.1
- torchvision: 0.8.2
- Other dependencies
- Girum & IAMjmj give some valuable comments in the Github Issue part, and I just clarify some missed points of this paper. Please visit there for more information.
@inproceedings{jiang2022towards,
title={Towards federated learning against noisy labels via local self-regularization},
author={Jiang, Xuefeng and Sun, Sheng and Wang, Yuwei and Liu, Min},
booktitle={Proceedings of the 31st ACM International Conference on Information \& Knowledge Management},
pages={862--873},
year={2022}
}