Federated Active Learning Under Extreme Non-IID and Global Class Imbalance

• URL: http://arxiv.org/abs/2603.10341v1
• Date: Wed, 11 Mar 2026 02:22:10 GMT
• Title: Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
• Abstract summary: Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints.<n>We propose FairFAL, an adaptive class-fair FAL framework.<n> Experiments on five benchmarks show that FairFAL consistently outperforms state-of-the-art approaches.
• Score: 41.48995094786491
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints, yet its effectiveness degrades in realistic settings with severe global class imbalance and highly heterogeneous clients. We conduct a systematic study of query-model selection in FAL and uncover a central insight: the model that achieves more class-balanced sampling, especially for minority classes, consistently leads to better final performance. Moreover, global-model querying is beneficial only when the global distribution is highly imbalanced and client data are relatively homogeneous; otherwise, the local model is preferable. Based on these findings, we propose FairFAL, an adaptive class-fair FAL framework. FairFAL (1) infers global imbalance and local-global divergence via lightweight prediction discrepancy, enabling adaptive selection between global and local query models; (2) performs prototype-guided pseudo-labeling using global features to promote class-aware querying; and (3) applies a two-stage uncertainty-diversity balanced sampling strategy with k-center refinement. Experiments on five benchmarks show that FairFAL consistently outperforms state-of-the-art approaches under challenging long-tailed and non-IID settings. The code is available at https://github.com/chenchenzong/FairFAL.

Related papers

• FedReLa: Imbalanced Federated Learning via Re-Labeling [47.73320550761897]
  Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation.<n>The agnosticism of global class distribution poses significant challenges for data-level methods.<n>We propose FedReLa, a novel data-level approach that tackles the coexistence of data heterogeneity and class imbalance in federated learning.
  arXiv  Detail & Related papers  (2026-06-24T17:13:41Z)
• FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning [23.38141950440522]
  We propose a controllable federated group-fairness calibration framework, named FedFACT.<n>FedFACT identifies the Bayes-optimal classifiers under both global and local fairness constraints.<n>We show that FedFACT consistently outperforms baselines in balancing accuracy and global-local fairness.
  arXiv  Detail & Related papers  (2025-06-04T09:39:57Z)
• Mind the Gap: Confidence Discrepancy Can Guide Federated Semi-Supervised Learning Across Pseudo-Mismatch [50.632535091877706]
  Federated Semi-Supervised Learning (FSSL) aims to leverage unlabeled data across clients with limited labeled data to train a global model with strong generalization ability.<n>Most FSSL methods rely on consistency regularization with pseudo-labels, converting predictions from local or global models into hard pseudo-labels as supervisory signals.<n>We show that the quality of pseudo-label is largely deteriorated by data heterogeneity, an intrinsic facet of federated learning.
  arXiv  Detail & Related papers  (2025-03-17T14:41:51Z)
• Federated Skewed Label Learning with Logits Fusion [23.062650578266837]
  Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. We propose FedBalance, which corrects the optimization bias among local models by calibrating their logits. Our method can gain 13% higher average accuracy compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-11-14T14:37:33Z)
• Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
  Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. We find that the difference in logits between the local and global models increases as the model is continuously updated. We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
  arXiv  Detail & Related papers  (2023-08-20T04:41:01Z)
• Re-thinking Federated Active Learning based on Inter-class Diversity [16.153683223016973]
  We show that the superiority of two selector models depends on the global and local inter-class diversity. We propose LoGo, a FAL sampling strategy robust to varying local heterogeneity levels and global imbalance ratio. LoGo consistently outperforms six active learning strategies in the total number of 38 experimental settings.
  arXiv  Detail & Related papers  (2023-03-22T05:21:21Z)
• Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning [60.41501515192088]
  Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively. The data samples usually follow a long-tailed distribution in the real world, and FL on the decentralized and long-tailed data yields a poorly-behaved global model. In this work, we integrate the local real data with the global gradient prototypes to form the local balanced datasets.
  arXiv  Detail & Related papers  (2023-01-25T03:18:10Z)
• Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction [76.26710990597498]
  We show that the class-imbalance of the grouped data from randomly selected clients can lead to significant performance degradation. Based on our key observation, we design an efficient client sampling mechanism, i.e., Federated Class-balanced Sampling (Fed-CBS) In particular, we propose a measure of class-imbalance and then employ homomorphic encryption to derive this measure in a privacy-preserving way.
  arXiv  Detail & Related papers  (2022-09-30T05:42:56Z)
• An Experimental Study of Class Imbalance in Federated Learning [0.8122270502556371]
  We propose two new metrics to define class imbalance -- the global class imbalance degree (MID) and the local difference of class imbalance among clients (WCS) Our results show that a higher MID and a larger WCS degrade more the performance of the global model.
  arXiv  Detail & Related papers  (2021-09-09T08:26:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.