FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification

TL;DR

FedSI introduces a scalable Bayesian federated learning framework that efficiently quantifies uncertainty by inferring client-specific subnetworks, outperforming existing methods in heterogeneous data scenarios.

Contribution

It proposes a novel subnetwork inference approach in federated learning that balances efficiency and uncertainty quantification, addressing limitations of prior Bayesian FL methods.

Findings

FedSI outperforms existing Bayesian and non-Bayesian FL methods.

It achieves fast, scalable inference with effective uncertainty preservation.

Demonstrated on three benchmark datasets with heterogeneous data.

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 over-simplified model structures or high computational and memory costs. In this paper, we introduce FedSI, a novel Bayesian DNNs-based subnetwork inference PFL framework. FedSI is simple and scalable by leveraging Bayesian methods to incorporate systematic uncertainties effectively. It implements a client-specific subnetwork inference 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 three different benchmark datasets demonstrate that FedSI outperforms existing Bayesian and non-Bayesian FL baselines in heterogeneous FL scenarios.