FedX: Unsupervised Federated Learning with Cross Knowledge Distillation

Sungwon Han, Sungwon Park, Fangzhao Wu, Sundong Kim, Chuhan Wu +2 more
7/19/2022
cs.CVcs.LG

No official code found. Best implementation: Sungwon-Han/FEDX (73 stars, last commit 2022-08-23).

Abstract

This paper presents FedX, an unsupervised federated learning framework. Our model learns unbiased representation from decentralized and heterogeneous local data. It employs a two-sided knowledge distillation with contrastive learning as a core component, allowing the federated system to function without requiring clients to share any data features. Furthermore, its adaptable architecture can be used as an add-on module for existing unsupervised algorithms in federated settings. Experiments show that our model improves performance significantly (1.58--5.52pp) on five unsupervised algorithms.

View on arXivView PDF

Code Implementations(1)

Sungwon-Han/FEDXCommunity100%
7312PythonJul 4, 20224 years ago

Similar Papers

Federated Clustering: An Unsupervised Cluster-Wise Training for Decentralized Data Distributions

86% match2024

DFML: Decentralized Federated Mutual Learning

85% match2024

Relaxed Contrastive Learning for Federated Learning

85% match1 repo272024

HFedCKD: Toward Robust Heterogeneous Federated Learning via Data-free Knowledge Distillation and Two-way Contrast

85% match2025

MultiConfederated Learning: Inclusive Non-IID Data handling with Decentralized Federated Learning

84% match2024

Federated Learning of Shareable Bases for Personalization-Friendly Image Classification

84% match2023

Cite this paper

@article{han2022fedx,
  title  = {FedX: Unsupervised Federated Learning with Cross Knowledge Distillation},
  author = {Sungwon Han and Sungwon Park and Fangzhao Wu and Sundong Kim and Chuhan Wu and Xing Xie and Meeyoung Cha},
  year   = {2022},
  eprint = {2207.09158},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.09158v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.09158.svg)](https://codeofpaper.com/paper/2207.09158)

Discussion