/FedoSSL

code for paper "Towards Unbiased Training in Federated Open-world Semi-supervised Learning"

Primary LanguagePython

Towards Unbiased Training in Federated Open-world Semi-supervised Learning

This repo contains the reference source code in PyTorch of the FedoSSL algorithm. For more details please check our paper Towards Unbiased Training in Federated Open-world Semi-supervised Learning (ICML '23).

Dependencies

The code is built with the following libraries:

Usage

Get Started

We use SimCLR for pretraining. The weights used in our paper can be downloaded in this link.

  • To train on CIFAR-100, run
python fedossl_cifar.py --dataset cifar100 --labeled-num 50 --labeled-ratio 0.5
  • To train on ImageNet-100, first use gen_imagenet_list.py to generate corresponding splitting lists, then run
python fedossl_imagenet.py --labeled-num 50 --labeled-ratio 0.5