Federated PAC-Bayesian Learning on Non-IID Data
Federated PAC-Bayesian Learning on Non-IID Data
Zihao Zhao,Yang Liu,Wenbo Ding,Xiaoping Zhang
TLDR
This work presents the first non-vacuous federated PAC-Bayesian bound tailored for non-IID local data, which assumes unique prior knowledge for each client and variable aggregation weights.
Abstract
Existing research has either adapted the Probably Approximately Correct (PAC) Bayesian framework for federated learning (FL) or used information-theoretic PAC-Bayesian bounds while introducing their theorems, but few consider the non-IID challenges in FL. Our work presents the first non-vacuous federated PAC-Bayesian bound tailored for non-IID local data. This bound assumes unique prior knowledge for each client and variable aggregation weights. We also introduce an objective function and an innovative Gibbs-based algorithm for the optimization of the derived bound. The results are validated on real-world datasets.