Reliable Federated Disentangling Network for Non-IID Domain Feature

TL;DR

This paper introduces RFedDis, a federated learning model that disentangles features and incorporates uncertainty estimation to improve reliability and performance in non-IID domain scenarios.

Contribution

RFedDis is the first federated learning approach combining evidential uncertainty with feature disentangling for enhanced reliability and accuracy in non-IID domain feature settings.

Findings

RFedDis outperforms existing FL methods in accuracy.

RFedDis provides more reliable predictions with uncertainty estimation.

The approach effectively handles non-IID domain feature shifts.

Abstract

Federated learning (FL), as an effective decentralized distributed learning approach, enables multiple institutions to jointly train a model without sharing their local data. However, the domain feature shift caused by different acquisition devices/clients substantially degrades the performance of the FL model. Furthermore, most existing FL approaches aim to improve accuracy without considering reliability (e.g., confidence or uncertainty). The predictions are thus unreliable when deployed in safety-critical applications. Therefore, aiming at improving the performance of FL in non-Domain feature issues while enabling the model more reliable. In this paper, we propose a novel reliable federated disentangling network, termed RFedDis, which utilizes feature disentangling to enable the ability to capture the global domain-invariant cross-client representation and preserve local client-specific feature learning. Meanwhile, to effectively integrate the decoupled features, an uncertainty-aware decision fusion is also introduced to guide the network for dynamically integrating the decoupled features at the evidence level, while producing a reliable prediction with an estimated uncertainty. To the best of our knowledge, our proposed RFedDis is the first work to develop an FL approach based on evidential uncertainty combined with feature disentangling, which enhances the performance and reliability of FL in non-IID domain features. Extensive experimental results show that our proposed RFedDis provides outstanding performance with a high degree of reliability as compared to other state-of-the-art FL approaches.