Towards Personalized Federated Learning
It tackles the problem of training effective models on decentralized, heterogeneous data for applications requiring privacy, but is incremental as a survey rather than a novel method.
This survey addresses the challenge of data heterogeneity in Federated Learning by exploring Personalized Federated Learning (PFL) to improve model performance on diverse real-world datasets, presenting a taxonomy of techniques and outlining future research directions.
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.