Work

FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification

Year: 2025

Type: article

Abstract: While deep neural networks (DNNs)-based personalized federated learning (PFL) is demanding for addressing data heterogeneity and shows promising performance, existing methods for federated learning (FL) suffer from efficient systematic uncertainty quantification. The Bayesian DNNs-based PFL is usually questioned of either oversimplified model structures or high computational and memory costs. In this article, we introduce FedSI, a novel Bayesian DNNs-based subnetwork inference (SI) PFL framework. FedSI is simple and scalable by leveraging Bayesian methods to incorporate systematic uncertainties effectively. It implements a client-specific SI mechanism, selects network parameters with large variance to be inferred through posterior distributions, and fixes the rest as deterministic ones. FedSI achieves fast and scalable inference while preserving the systematic uncertainties to the fullest extent. Extensive experiments on four different benchmark datasets demonstrate that FedSI outperforms existing Bayesian and non-Bayesian FL baselines in heterogeneous FL scenarios.

Source: IEEE Transactions on Neural Networks and Learning Systems

DOI: 10.1109/tnnls.2025.3562164

Authors: Hui Chen, Hengyu Liu, Zhangkai Wu, Xuhui Fan, Longbing Cao

Institutions: Macquarie University, Aalborg University, University of Technology Sydney

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Australian Research Council

Awards: Data Complexity and Uncertainty-Resilient Deep Variational Learning, Deep Interaction Learning in Unlabelled Big Data and Complex Systems, Ethical Enterprise Representations for Personalised Sustainable Finance, Federated Omniverse Facilities for Smart Digital Futures, Deep analytics of non-occurring but important behaviours