Personalized Federated Learning With Differential Privacy and Convergence Guarantee

Personalized federated learning (PFL), as a novel federated learning (FL) paradigm, is capable of generating personalized models for heterogenous clients. Combined with with a meta-learning mechanism, PFL can further improve the convergence performance with few-shot training. However, meta-learning based PFL has two stages of gradient descent in each local training round, therefore posing a more serious challenge in information leakage. In this paper, we propose a differential privacy (DP) based PFL (DP-PFL) framework and analyze its convergence performance. Specifically, we first design a privacy budget allocation scheme for inner and outer update stages based on the Rényi DP composition theory. Then, we…

• NS
  National Science Foundation

  Award: CNS-2128448
• NN
  National Natural Science Foundation of China

  Awards: 62002170, 62071296
• FR
  Fundamental Research Funds for the Central Universities

  Award: 30921013104