PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning

Authors:
  • YFYu Feng
    Yu Feng
  • YGYangli-Ao Geng
    Yangli-Ao Geng
  • YZYifan Zhu
    Yifan Zhu
  • ZHZongfu Han
    Zongfu Han
  • XYXie Yu
    Xie Yu
  • KXKaiwen Xue
    Kaiwen Xue
  • HLHaoran Luo
    Haoran Luo
  • MSMengyang Sun
    Mengyang Sun
  • GZGuangwei Zhang
    Guangwei Zhang
  • MSMeina Song
    Meina Song

Abstract
Federated learning (FL) has gained widespread attention for its privacy-preserving and collaborative learning capabilities. Due to significant statistical heterogeneity, traditional FL struggles to generalize a shared model across diverse data domains. Personalized federated learning addresses this issue by dividing the model into a globally shared part and a locally private part, with the local model correcting representation biases introduced by the global model. Nevertheless, locally converged parameters more accurately capture domain-specific knowledge, and current methods overlook the potential benefits of these parameters. To address these limitations, we propose PM-MoE architecture. This architecture integrates a mixture of personalized modules and an energy-based personalized modules denoising, enabling each client to select beneficial personalized parameters from other clients. We applied the PM-MoE architecture to nine recent model-split-based personalized federated learning algorithms, achieving performance improvements with minimal additional training. Extensive experiments on six widely adopted datasets and two heterogeneity settings validate the effectiveness of our approach. The source code is available at \url{https://github.com/dannis97500/PM-MOE}.
All Related Versions