Bayesian Federated Learning: A Survey

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.

Authors

• Longbing Cao Macquarie University
• Hui Chen
• Xuhui Fan Macquarie University
• Joao Gama
• Yew-Soon Ong Centre for Frontier AI Research, A*STAR & College of Computing and Data Science, NTU
• Vipin Kumar

Keywords

• Survey: Data Mining
• Survey: Machine Learning
• Survey: Multidisciplinary Topics and Applications
• Survey: Uncertainty in AI