LGJun 8, 2023

Federated Learning under Covariate Shifts with Generalization Guarantees

arXiv:2306.05325v112 citationsh-index: 60
Originality Highly original
AI Analysis

It addresses data distribution shifts across clients in federated learning, which is an incremental improvement for privacy-sensitive applications.

The paper tackles covariate shifts in federated learning by proposing FTW-ERM, a method that improves generalization error over classical ERM, with experimental results showing superiority in imbalanced settings.

This paper addresses intra-client and inter-client covariate shifts in federated learning (FL) with a focus on the overall generalization performance. To handle covariate shifts, we formulate a new global model training paradigm and propose Federated Importance-Weighted Empirical Risk Minimization (FTW-ERM) along with improving density ratio matching methods without requiring perfect knowledge of the supremum over true ratios. We also propose the communication-efficient variant FITW-ERM with the same level of privacy guarantees as those of classical ERM in FL. We theoretically show that FTW-ERM achieves smaller generalization error than classical ERM under certain settings. Experimental results demonstrate the superiority of FTW-ERM over existing FL baselines in challenging imbalanced federated settings in terms of data distribution shifts across clients.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes