Bayesian Federated Learning: A Survey
It addresses robustness and explainability issues in federated learning for privacy-preserving distributed systems, but is incremental as a survey.
This survey tackles the challenges of federated learning, such as data limitations and uncertainties, by providing a critical overview of Bayesian federated learning, categorizing methods and discussing their pros and cons.
Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. However, the robustness and capabilities of existing FL methods are challenged by limited and dynamic data and conditions, complexities including heterogeneities and uncertainties, and analytical explainability. Bayesian federated learning (BFL) has emerged as a promising approach to address these issues. This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives. We categorize and discuss client- and server-side and FL-based BFL methods and their pros and cons. The limitations of the existing BFL methods and the future directions of BFL research further address the intricate requirements of real-life FL applications.