Exploring the Possibility of TypiClust for Low-Budget Federated Active Learning

TL;DR

This paper evaluates TypiClust, a low-budget active learning strategy, in federated active learning scenarios, demonstrating its robustness and effectiveness despite challenges like data heterogeneity and distribution shifts.

Contribution

It provides empirical evidence that TypiClust performs well in low-budget federated active learning settings, addressing challenges of data heterogeneity and distribution shifts.

Findings

TypiClust outperforms other methods in low-budget FAL.

FAL settings induce distribution shifts in data.

TypiClust is robust to typicality-based distribution shifts.

Abstract

Federated Active Learning (FAL) seeks to reduce the burden of annotation under the realistic constraints of federated learning by leveraging Active Learning (AL). As FAL settings make it more expensive to obtain ground truth labels, FAL strategies that work well in low-budget regimes, where the amount of annotation is very limited, are needed. In this work, we investigate the effectiveness of TypiClust, a successful low-budget AL strategy, in low-budget FAL settings. Our empirical results show that TypiClust works well even in low-budget FAL settings contrasted with relatively low performances of other methods, although these settings present additional challenges, such as data heterogeneity, compared to AL. In addition, we show that FAL settings cause distribution shifts in terms of typicality, but TypiClust is not very vulnerable to the shifts. We also analyze the sensitivity of TypiClust to feature extraction methods, and it suggests a way to perform FAL even in limited data situations.