FedNN: Federated learning on concept drift data using weight and adaptive group normalizations

Myeongkyun Kang, Soopil Kim, Kyong Hwan Jin, Ehsan Adeli, Kilian M. Pohl, Sanghyun Park

Abstract: Highlights•We investigate FL with concept drift on newly constructed datasets•We show that weight normalization can reduce weight drifts from heterogeneous clients•We show that adaptive group normalization can improve robustness to diverse data shifts•FedNN improves the performance of existing FL methods on seven datasets