English

Towards Personalized Federated Learning via Comprehensive Knowledge Distillation

Machine Learning 2024-11-07 v1 Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition

Abstract

Federated learning is a distributed machine learning paradigm designed to protect data privacy. However, data heterogeneity across various clients results in catastrophic forgetting, where the model rapidly forgets previous knowledge while acquiring new knowledge. To address this challenge, personalized federated learning has emerged to customize a personalized model for each client. However, the inherent limitation of this mechanism is its excessive focus on personalization, potentially hindering the generalization of those models. In this paper, we present a novel personalized federated learning method that uses global and historical models as teachers and the local model as the student to facilitate comprehensive knowledge distillation. The historical model represents the local model from the last round of client training, containing historical personalized knowledge, while the global model represents the aggregated model from the last round of server aggregation, containing global generalized knowledge. By applying knowledge distillation, we effectively transfer global generalized knowledge and historical personalized knowledge to the local model, thus mitigating catastrophic forgetting and enhancing the general performance of personalized models. Extensive experimental results demonstrate the significant advantages of our method.

Keywords

Cite

@article{arxiv.2411.03569,
  title  = {Towards Personalized Federated Learning via Comprehensive Knowledge Distillation},
  author = {Pengju Wang and Bochao Liu and Weijia Guo and Yong Li and Shiming Ge},
  journal= {arXiv preprint arXiv:2411.03569},
  year   = {2024}
}

Comments

Accepted by IEEE SMC 2024

R2 v1 2026-06-28T19:49:38.441Z