Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) Vol. 2022; pp. 10051 - 10061
• Main Authors: Qu, Liangqiong, Zhou, Yuyin, Liang, Paul Pu, Xia, Yingda, Wang, Feifei, Adeli, Ehsan, Fei-Fei, Li, Rubin, Daniel
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.06.2022
• Subjects: Computer architecture; Data models; Federated learning; Organizations; Privacy and federated learning; Robustness; Training; Transformers

Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental challenges such as the lack of convergence and the potential...