Towards Personalized Federated Learning

TL;DR

This paper surveys personalized federated learning, addressing challenges of data heterogeneity, and discusses future research directions for privacy-preserving, personalized AI models across decentralized data sources.

Contribution

It provides a comprehensive taxonomy of PFL techniques, analyzing their motivations, challenges, and opportunities, and outlines future research trajectories.

Findings

Taxonomy categorizes PFL techniques by challenges and strategies.

Identifies key challenges and opportunities in PFL.

Envisions future directions for PFL architecture and benchmarking.

Abstract

In parallel with the rapid adoption of Artificial Intelligence (AI) empowered by advances in AI research, there have been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest towards privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of Personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges and opportunities and envision promising future trajectories of research towards new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.