Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

Junyuan Hong (Michigan State University)

Junyuan Hong is a Ph.D. student in the Computer Science and Engineering Department at Michigan State University (MSU) working with Jiayu Zhou. His research interests are in federated learning, and privacy-preserving learning. Prior to MSU, he received his Master’s and Bachelor’s degrees in Computer Science and Physics from University of Science and Technology of China, respectively.

Short Abstract: Federated learning (FL) provides a distributed learning framework for multiple participants to collaborate learning without sharing raw data. In many practical FL scenarios, participants have heterogeneous resources due to disparities in hardware and inference dynamics that require quickly loading models of different sizes and levels of robustness. The heterogeneity and dynamics together impose significant challenges to existing FL approaches and thus greatly limit FL’s applicability. In this talk, I talk about a novel Split-Mix FL strategy for heterogeneous participants that, once training is done, provides in-situ customization of model sizes and robustness. This split-mix strategy achieves customization with high efficiency in communication, storage, and inference. Extensive experiments demonstrate that our method provides better in-situ customization than the existing heterogeneous-architecture FL methods.