Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization

TL;DR

This paper introduces a novel federated learning approach called Federated Prototype Rectification with Personalization, designed to effectively handle skewed data distributions across clients, improving model fairness and performance.

Contribution

It redefines the challenging setting of skewed heterogeneous federated learning and proposes a new method combining personalization and prototype rectification for better handling data imbalance.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Achieves balanced performance in personalization and generalization.

Effectively addresses data skewness in federated learning.

Abstract

Federated learning is an efficient framework designed to facilitate collaborative model training across multiple distributed devices while preserving user data privacy. A significant challenge of federated learning is data-level heterogeneity, i.e., skewed or long-tailed distribution of private data. Although various methods have been proposed to address this challenge, most of them assume that the underlying global data is uniformly distributed across all clients. This paper investigates data-level heterogeneity federated learning with a brief review and redefines a more practical and challenging setting called Skewed Heterogeneous Federated Learning (SHFL). Accordingly, we propose a novel Federated Prototype Rectification with Personalization which consists of two parts: Federated Personalization and Federated Prototype Rectification. The former aims to construct balanced decision boundaries between dominant and minority classes based on private data, while the latter exploits both inter-class discrimination and intra-class consistency to rectify empirical prototypes. Experiments on three popular benchmarks show that the proposed approach outperforms current state-of-the-art methods and achieves balanced performance in both personalization and generalization.