Federated PAC-Bayesian Learning on Non-IID data

Zihao Zhao, Yang Liu, Wenbo Ding, Xiao-Ping Zhang
9/13/2023
cs.LGcs.DC

No confident code implementation found for this paper.

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 considering 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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Personalized Federated Learning of Probabilistic Models: A PAC-Bayesian Approach

86% match2024

Information-Geometric Barycenters for Bayesian Federated Learning

83% match2024

Federated Learning via Variational Bayesian Inference: Personalization, Sparsity and Clustering

83% match2023

Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization

82% match2024

Federated Bayesian Deep Learning: The Application of Statistical Aggregation Methods to Bayesian Models

81% match2024

FedHB: Hierarchical Bayesian Federated Learning

81% match2023

Cite this paper

@article{zhao2023federated,
  title  = {Federated PAC-Bayesian Learning on Non-IID data},
  author = {Zihao Zhao and Yang Liu and Wenbo Ding and Xiao-Ping Zhang},
  year   = {2023},
  eprint = {2309.06683},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.06683v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.06683.svg)](https://codeofpaper.com/paper/2309.06683)

Discussion