---
title: "Inconsistency-Based Federated Active Learning"
authors:
  - "Chen-Chen Zong"
  - "Tong Jin"
  - "Sheng-Jun Huang"
doi: "10.24963/ijcai.2025/812"
url: "https://ijcai.org/proceedings/2025/812"
pdf: "https://ijcai.org/proceedings/2025/0812.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "7300-7308"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Active learning"
  - "Machine Learning: ML: Weakly supervised learning"
  - "Machine Learning: ML: Federated learning"
  - "Machine Learning: ML: Classification"
---

# Inconsistency-Based Federated Active Learning

Chen-Chen Zong, Tong Jin, Sheng-Jun Huang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 7300-7308. DOI: [10.24963/ijcai.2025/812](https://doi.org/10.24963/ijcai.2025/812)

## 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.