Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 34, Issue 12, Pages 9587-9603Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2022.3160699
Keywords
Data models; Training; Adaptation models; Collaborative work; Data privacy; Servers; Faces; Edge computing; federated learning (FL); non-IID data; personalized FL (PFL); privacy preservation; statistical heterogeneity
Ask authors/readers for more resources
With the rapid advancement of artificial intelligence, there is increasing concern about data privacy. Federated Learning (FL) has become popular as a privacy-preserving training method for machine learning models. In this survey, personalized FL is explored to address the challenges of FL on heterogeneous data.
In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward 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, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available