FedX: Unsupervised Federated Learning with Cross Knowledge Distillation

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.

Cite

Text

Han et al. "FedX: Unsupervised Federated Learning with Cross Knowledge Distillation." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-20056-4_40

Markdown

[Han et al. "FedX: Unsupervised Federated Learning with Cross Knowledge Distillation." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/han2022eccv-fedx/) doi:10.1007/978-3-031-20056-4_40

BibTeX

@inproceedings{han2022eccv-fedx,
  title     = {{FedX: Unsupervised Federated Learning with Cross Knowledge Distillation}},
  author    = {Han, Sungwon and Park, Sungwon and Wu, Fangzhao and Kim, Sundong and Wu, Chuhan and Xie, Xing and Cha, Meeyoung},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2022},
  doi       = {10.1007/978-3-031-20056-4_40},
  url       = {https://mlanthology.org/eccv/2022/han2022eccv-fedx/}
}