Sorry, you need to enable JavaScript to visit this website.

Federated PAC-Bayesian Learning on Non-IID Data

DOI:
10.60864/1rxy-as96
Citation Author(s):
Submitted by:
Zihao Zhao
Last updated:
6 June 2024 - 10:32am
Document Type:
Poster
Document Year:
2024
Event:
Presenters:
Zihao Zhao
Paper Code:
MLSP-P10.5
 

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.

up
1 user has voted: Zihao Zhao