Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regression
It addresses task diversity in federated learning for applications with heterogeneous local devices, representing an incremental advance by integrating multi-task learning into the federated framework.
This paper tackles the limitation of federated learning in handling diverse tasks like classification and regression simultaneously, proposing a Bayesian multi-task approach that improves predictive performance, uncertainty calibration, and convergence rate in experiments.
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 Pólya-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.