Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization

TL;DR

This paper introduces an efficient second-order optimization method for Bayesian federated learning that enhances personalization, uncertainty estimation, and predictive accuracy while reducing computational and communication costs.

Contribution

The paper proposes a novel second-order optimization approach for Bayesian federated learning, significantly improving efficiency and accuracy over existing Bayesian FL methods.

Findings

Achieves higher predictive accuracy than baseline methods.

Provides better uncertainty estimates in federated learning.

Reduces computational and communication costs compared to prior Bayesian FL approaches.

Abstract

Federated Learning (FL) has emerged as a promising method to collaboratively learn from decentralized and heterogeneous data available at different clients without the requirement of data ever leaving the clients. Recent works on FL have advocated taking a Bayesian approach to FL as it offers a principled way to account for the model and predictive uncertainty by learning a posterior distribution for the client and/or server models. Moreover, Bayesian FL also naturally enables personalization in FL to handle data heterogeneity across the different clients by having each client learn its own distinct personalized model. In particular, the hierarchical Bayesian approach enables all the clients to learn their personalized models while also taking into account the commonalities via a prior distribution provided by the server. However, despite their promise, Bayesian approaches for FL can be computationally expensive and can have high communication costs as well because of the requirement of computing and sending the posterior distributions. We present a novel Bayesian FL method using an efficient second-order optimization approach, with a computational cost that is similar to first-order optimization methods like Adam, but also provides the various benefits of the Bayesian approach for FL (e.g., uncertainty, personalization), while also being significantly more efficient and accurate than SOTA Bayesian FL methods (both for standard as well as personalized FL settings). Our method achieves improved predictive accuracies as well as better uncertainty estimates as compared to the baselines which include both optimization based as well as Bayesian FL methods.