[Official] FedBABU: Toward Enhanced Representation for Federated Image Classification

This repository is the official implementation of "FedBABU: Towards Enhanced Representation for Federated Image Classification" paper presented in ICLR 2022. Thanks to the contributors. [Paper]

Installation

First check that the requirements are satisfied:
Python 3.6
torch 1.2.0
torchvision 0.4.0
numpy 1.18.1
sklearn 0.20.0
matplotlib 3.1.2
Pillow 4.1.1

The next step is to clone the repository:

git clone https://github.com/jhoon-oh/FedBABU.git

Data

We run FedBABU and other FL algorithms experiments on CIFAR10 and CIFAR100 using 4convNet, mobileNet, and ResNet.

Script for running

Please refer to ./scripts folder.

Contact

Feel free to contact us if you have any questions:)

• Jaehoon Oh: jhoon.oh@kaist.ac.kr
• SangMook Kim: sangmook.kim@kaist.ac.kr

Acknowledgements

This codebase was adapted from https://github.com/pliang279/LG-FedAvg.