Federated Learning Without Labels
Last updated on
Mar 9, 2022


Weiming Zhuang
Research Scientist
My current research interests include federated learning, computer vison, self-supervised learning, and machine learning system.
Publications
We propose a novel federated unsupervised learning framework, FedU, to learn visual representation from decentralized data while preserving data prviacy. To tackle non-IID challenge, we propose two simple but effective methods: 1) We design the communication protocol to upload and update only the online encoders; 2) We introduce a new module to dynamically decide how to update predictors based on the divergence caused by non-IID.
Weiming Zhuang,
Xin Gan,
Yonggang Wen,
Shuai Zhang,
Shuai Yi