Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy

• URL: http://arxiv.org/abs/2510.07022v1
• Date: Wed, 08 Oct 2025 13:47:19 GMT
• Title: Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy
• Authors: ZiHeng Huang, Di Wu, Jun Bai, Jiale Zhang, Sicong Cao, Ji Zhang, Yingjie Hu,
• Abstract summary: Machine unlearning is critical for enforcing data deletion rights like the "right to be forgotten"<n>As a decentralized paradigm, Federated Learning (FL) also requires unlearning.<n>We propose a novel, fairness-aware FU approach, Federated Cross-Client-Constrains Unlearning (FedCCCU)
• Score: 17.398539259901483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine unlearning is critical for enforcing data deletion rights like the "right to be forgotten." As a decentralized paradigm, Federated Learning (FL) also requires unlearning, but realistic implementations face two major challenges. First, fairness in Federated Unlearning (FU) is often overlooked. Exact unlearning methods typically force all clients into costly retraining, even those uninvolved. Approximate approaches, using gradient ascent or distillation, make coarse interventions that can unfairly degrade performance for clients with only retained data. Second, most FU evaluations rely on synthetic data assumptions (IID/non-IID) that ignore real-world heterogeneity. These unrealistic benchmarks obscure the true impact of unlearning and limit the applicability of current methods. We first conduct a comprehensive benchmark of existing FU methods under realistic data heterogeneity and fairness conditions. We then propose a novel, fairness-aware FU approach, Federated Cross-Client-Constrains Unlearning (FedCCCU), to explicitly address both challenges. FedCCCU offers a practical and scalable solution for real-world FU. Experimental results show that existing methods perform poorly in realistic settings, while our approach consistently outperforms them.

Related papers

• Fairness Regularization in Federated Learning [1.4773243280881763]
  Federated Learning (FL) has emerged as a vital paradigm in modern machine learning.<n>This work focuses on performance equitable fairness, which aims to minimize differences in performance across clients.<n>We empirically show that FairGrad (approximate) and FairGrad* (exact) improve both fairness and overall model performance in heterogeneous data settings.
  arXiv  Detail & Related papers  (2025-08-16T13:32:41Z)
• Federated Unlearning Made Practical: Seamless Integration via Negated Pseudo-Gradients [3.12131298354022]
  This paper introduces a novel method that leverages negated Pseudo-gradients Updates for Federated Unlearning (PUF)<n>Our approach only uses standard client model updates, anyway employed during regular FL rounds, and interprets them as pseudo-gradients.<n>Unlike state-of-the-art mechanisms, PUF seamlessly integrates with FL, incurs no additional computational and communication overhead beyond standard FL rounds, and supports concurrent unlearning requests.
  arXiv  Detail & Related papers  (2025-04-08T09:05:33Z)
• Accurate Forgetting for Heterogeneous Federated Continual Learning [89.08735771893608]
  We propose a new concept accurate forgetting (AF) and develop a novel generative-replay methodMethodwhich selectively utilizes previous knowledge in federated networks.<n>We employ a probabilistic framework based on a normalizing flow model to quantify the credibility of previous knowledge.
  arXiv  Detail & Related papers  (2025-02-20T02:35:17Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Communication Efficient and Provable Federated Unlearning [43.178460522012934]
  We study federated unlearning, a novel problem to eliminate the impact of specific clients or data points on the global model learned via federated learning (FL) This problem is driven by the right to be forgotten and the privacy challenges in FL. We introduce a new framework for exact federated unlearning that meets two essential criteria: textitcommunication efficiency and textitexact unlearning provability.
  arXiv  Detail & Related papers  (2024-01-19T20:35:02Z)
• Fair Machine Unlearning: Data Removal while Mitigating Disparities [5.724350004671127]
  Right to be forgotten is core principle outlined by EU's General Regulation. "Forgetting" can be naively achieved by retraining on remaining data. "Unlearning" impacts other properties critical to real-world applications such as fairness.
  arXiv  Detail & Related papers  (2023-07-27T10:26:46Z)
• Combating Exacerbated Heterogeneity for Robust Models in Federated Learning [91.88122934924435]
  Combination of adversarial training and federated learning can lead to the undesired robustness deterioration. We propose a novel framework called Slack Federated Adversarial Training (SFAT) We verify the rationality and effectiveness of SFAT on various benchmarked and real-world datasets.
  arXiv  Detail & Related papers  (2023-03-01T06:16:15Z)
• Preventing Discriminatory Decision-making in Evolving Data Streams [8.952662914331901]
  Bias in machine learning has rightly received significant attention over the last decade. Most fair machine learning (fair-ML) work to address bias in decision-making systems has focused solely on the offline setting. Despite the wide prevalence of online systems in the real world, work on identifying and correcting bias in the online setting is severely lacking.
  arXiv  Detail & Related papers  (2023-02-16T01:20:08Z)
• SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization [23.064896326146386]
  Machine Unlearning (MU) aims at removing the contribution of a given data point from a training procedure. While Federated Unlearning (FU) methods proposed, we propose SIFU (Sequential Informed Unlearning) as a new method.
  arXiv  Detail & Related papers  (2022-11-21T17:15:46Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning [61.488646649045215]
  Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices)
  arXiv  Detail & Related papers  (2021-11-28T19:03:39Z)
• Deep F-measure Maximization for End-to-End Speech Understanding [52.36496114728355]
  We propose a differentiable approximation to the F-measure and train the network with this objective using standard backpropagation. We perform experiments on two standard fairness datasets, Adult, Communities and Crime, and also on speech-to-intent detection on the ATIS dataset and speech-to-image concept classification on the Speech-COCO dataset. In all four of these tasks, F-measure results in improved micro-F1 scores, with absolute improvements of up to 8% absolute, as compared to models trained with the cross-entropy loss function.
  arXiv  Detail & Related papers  (2020-08-08T03:02:27Z)

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.