Litcius/Paper detail

FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification

Hui CHEN, Hengyu Liu, Zhangkai Wu, Xuhui Fan, Longbing Cao

2025IEEE Transactions on Neural Networks and Learning Systems6 citationsDOI

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.

Topics & Concepts

SubnetworkInferenceComputer scienceData scienceData miningArtificial intelligenceComputer networkEmbedded Systems Design TechniquesFault Detection and Control SystemsParallel Computing and Optimization Techniques
FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification | Litcius