What type of study is this?

This is a Quantitative Study study.

September 20, 2025

Inconsistency-Based Federated Active Learning

Key Points

IFAL outperforms existing methods in diverse query selection, improving learning outcomes in federated contexts.
Extensive experiments demonstrate more effective labeling methods, outperforming state-of-the-art alternatives on benchmark datasets.
Introduces inter-model and intra-model inconsistency criteria to enhance the performance of federated active learning.
Develops a data-driven probability formulation that aligns local and global model biases in weakly supervised scenarios.

Abstract

Federated learning (FL) enables distributed collaborative learning across local clients while preserving data privacy. However, its practical application in weakly supervised learning (WSL), where only a small subset of data is labeled, remains underexplored. Active learning (AL) is a promising solution for label-limited scenarios, but its adaptation to federated settings presents unique challenges, such as data heterogeneity and noise. In this paper, we propose Inconsistency-based Federated Active Learning (IFAL), a novel approach to address these challenges. First, we introduce a data-driven probability formulation that aligns the biases between local and global models in heterogeneous FL settings. Next, to mitigate noise, we propose an inter-model inconsistency criterion that filters out noisy examples and focuses on those with beneficial prediction discrepancies. Additionally, we introduce an intra-model inconsistency criterion to query examples that help refine the model’s decision boundaries. By combining these strategies with clustering, IFAL effectively selects a diverse and informative query set. Extensive experiments on benchmark datasets demonstrate that IFAL outperforms state-of-the-art methods.

KI fragen

Bookmark