Federated Active Learning for Target Domain Generalisation

TL;DR

This paper presents FEDALV, a novel federated active learning framework that enhances target domain generalization in image classification, achieving high accuracy with minimal data sharing by combining active learning and federated domain generalization techniques.

Contribution

The paper introduces FEDALV, integrating active learning with federated domain generalization, and demonstrates its effectiveness in improving accuracy with limited data sharing in unseen target domains.

Findings

FEDALV outperforms baseline methods in accuracy and efficiency.

Achieves target domain performance with only 5% data sampling.

Combines feature complexity reduction and regularization for better generalization.

Abstract

In this paper, we introduce Active Learning framework in Federated Learning for Target Domain Generalisation, harnessing the strength from both learning paradigms. Our framework, FEDALV, composed of Active Learning (AL) and Federated Domain Generalisation (FDG), enables generalisation of an image classification model trained from limited source domain client's data without sharing images to an unseen target domain. To this end, our FDG, FEDA, consists of two optimisation updates during training, one at the client and another at the server level. For the client, the introduced losses aim to reduce feature complexity and condition alignment, while in the server, the regularisation limits free energy biases between source and target obtained by the global model. The remaining component of FEDAL is AL with variable budgets, which queries the server to retrieve and sample the most informative local data for the targeted client. We performed multiple experiments on FDG w/ and w/o AL and compared with both conventional FDG baselines and Federated Active Learning baselines. Our extensive quantitative experiments demonstrate the superiority of our method in accuracy and efficiency compared to the multiple contemporary methods. FEDALV manages to obtain the performance of the full training target accuracy while sampling as little as 5% of the source client's data.