Awesome
Robust Federated Learning with Noisy and Heterogeneous Clients
This repository provides resources for the following paper:
[Robust Federated Learning with Noisy and Heterogeneous Client](CVPR 2022 Open Access Repository)
Xiuwen Fang, Mang Ye CVPR 2022
RHFL Description
RHFL (Robust Heterogeneous Federated Learning) is a federated learning framework to solve the robust federated learning problem with noisy and heterogeneous clients:
-
Aligning the logits output distributions in heterogeneous federated learning.
-
Local noise learning with a noise-tolerant loss function.
-
Client confidence re-weighting for external noise.
Framework Architecture
Dataset
Our experiments are conducted on two datasets, Cifar10 and Cifar100. We set public dataset on the server as a subset of Cifar100, and randomly divide Cifar10 to different clients as private datasets.
Dataset used: CIFAR-10、CIFAR-100
Note: Data will be processed in init_data.py
Quick Start
After installing MindSpore via the official website, you can start training and evaluation as follows:
# init public data and local data
python Dataset/init_data.py
# pretrain local models
python Network/pretrain.py
# RHFL
python HHF/HHF.py
Script and Sample Code
├── Robust_FL
├── Dataset
├── cifar.py
├── init_dataset.py
├── utils.py
├── Network
├── Models_Def
├── mobilnet_v2.py
├── resnet.py
├── shufflenet.py
├── pretrain.py
├── HHF
├── HHF.py
├── loss.py
├── README.md
Comparison with the SOTA methods
In the heterogeneous model scenario, we assign four different networks:ResNet10,ResNet12,ShuffleNet,Mobilenetv2
Citation
@inproceedings{fang2022robust,
title={Robust Federated Learning With Noisy and Heterogeneous Clients},
author={Fang, Xiuwen and Ye, Mang},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={10072--10081},
year={2022}
}