PPFL: A Personalized Federated Learning Framework for Heterogeneous Population

TL;DR

PPFL introduces a privacy-preserving, interpretable federated learning framework that models population heterogeneity through canonical models and membership vectors, providing insights into client preferences and outperforming existing methods.

Contribution

This work develops PPFL, a novel federated learning framework that captures client heterogeneity with interpretability and privacy, and introduces a new optimization algorithm with proven convergence.

Findings

PPFL effectively models heterogeneity in federated learning.

Experimental results show PPFL outperforms existing personalized FL methods.

PPFL provides interpretable insights into client preferences.

Abstract

Personalization aims to characterize individual preferences and is widely applied across many fields. However, conventional personalized methods operate in a centralized manner, potentially exposing raw data when pooling individual information. In this paper, with privacy considerations, we develop a flexible and interpretable personalized framework within the paradigm of federated learning, called \texttt{PPFL} (Population Personalized Federated Learning). By leveraging ``canonical models" to capture fundamental characteristics of a heterogeneous population and employing ``membership vectors" to reveal clients' preferences, \texttt{PPFL} models heterogeneity as clients' varying preferences for these characteristics. This approach provides substantial insights into client characteristics, which are lacking in existing Personalized Federated Learning (PFL) methods. Furthermore, we explore the relationship between \texttt{PPFL} and three main branches of PFL methods: clustered FL, multi-task PFL, and decoupling PFL, and demonstrate the advantages of \texttt{PPFL}. To solve \texttt{PPFL} (a non-convex optimization problem with linear constraints), we propose a novel random block coordinate descent algorithm and establish its convergence properties. We conduct experiments on both pathological and practical data sets, and the results validate the effectiveness of \texttt{PPFL}.