Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regression

TL;DR

This paper introduces a Bayesian federated learning framework that simultaneously handles classification and regression tasks on local devices using multi-output Gaussian processes, improving performance and uncertainty quantification.

Contribution

It presents a novel integration of multi-task learning with federated learning via multi-output Gaussian processes, addressing task diversity and computational challenges.

Findings

Superior predictive performance on synthetic and real data

Enhanced out-of-distribution detection and uncertainty calibration

Faster convergence and better scalability

Abstract

This work addresses a key limitation in current federated learning approaches, which predominantly focus on homogeneous tasks, neglecting the task diversity on local devices. We propose a principled integration of multi-task learning using multi-output Gaussian processes (MOGP) at the local level and federated learning at the global level. MOGP handles correlated classification and regression tasks, offering a Bayesian non-parametric approach that naturally quantifies uncertainty. The central server aggregates the posteriors from local devices, updating a global MOGP prior redistributed for training local models until convergence. Challenges in performing posterior inference on local devices are addressed through the P\'{o}lya-Gamma augmentation technique and mean-field variational inference, enhancing computational efficiency and convergence rate. Experimental results on both synthetic and real data demonstrate superior predictive performance, OOD detection, uncertainty calibration and convergence rate, highlighting the method's potential in diverse applications. Our code is publicly available at https://github.com/JunliangLv/task_diversity_BFL.