Federated Learning: Challenges, Methods, and Future Directions
This is an incremental review article that outlines challenges and methods for federated learning, relevant to researchers in machine learning, distributed systems, and privacy.
The paper addresses the challenges of training statistical models across remote devices or data centers while keeping data localized, and provides an overview of current methods and future directions for federated learning.
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.