mlsanityData to 14 Oct 2026

FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness

arXiv 2508.09866 ↗First posted 13 Aug 2025cs.LGcited by 0

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

To protect clients' right to be forgotten in federated learning, federated unlearning aims to remove the data contribution of leaving clients from the global learned model. While current studies mainly focused on enhancing unlearning efficiency and effectiveness, the crucial aspects of efficiency fairness and performance fairness among decentralized clients during unlearning have remained largely unexplored. In this study, we introduce FedShard, the first federated unlearning algorithm designed to concurrently guarantee both efficiency fairness and performance fairness. FedShard adaptively addresses the challenges introduced by dilemmas among convergence, unlearning efficiency, and unlearning fairness. Furthermore, we propose two novel metrics to quantitatively assess the fairness of unlearning algorithms, which we prove to satisfy well-known properties in other existing fairness measurements. Our theoretical analysis and numerical evaluation validate FedShard's fairness in terms of both unlearning performance and efficiency. We demonstrate that FedShard mitigates unfairness risks such as cascaded leaving and poisoning attacks and realizes more balanced unlearning costs among clients. Experimental results indicate that FedShard accelerates the data unlearning process 1.3-6.2 times faster than retraining from scratch and 4.9 times faster than the state-of-the-art exact unlearning methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 21 of its 53 references that are in the map. First posted on arXiv 13 Aug 2025.

Builds on

21 of 53 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Scalable Federated Unlearning via Isolated and Coded Sharding29 Jan
  2. 2024Communication Efficient and Provable Federated Unlearning19 Jan
  3. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar

Other references · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  4. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  5. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
  6. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  7. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
  8. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  9. 2020Fairness in Machine Learningcited by 194
  10. 2021A survey on datasets for fairness-aware machine learningcited by 157
  11. 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
  12. 2023Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projectioncited by 37
6 more
  1. 2018Data Poisoning Attacks against Online Learningcited by 27
  2. 2023Fair Machine Unlearning: Data Removal while Mitigating Disparitiescited by 26
  3. 2024Machine Unlearning via Null Space Calibrationcited by 21
  4. 2021Faithful Edge Federated Learning: Scalability and Privacycited by 13
  5. 2022FedSS: Federated Learning with Smart Selection of clientscited by 4
  6. 2023Adaptive Federated Learning via New Entropy Approachcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy
  2. 2024Federated Unlearning: a Perspective of Stability and Fairness
  3. 2023Exploring Federated Unlearning: Review, Comparison, and Insights
  4. 2026Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression
  5. 2024Streamlined Federated Unlearning: Unite as One to Be Highly Efficient
  6. 2024Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
  7. 2023Attacks on fairness in Federated Learning
  8. 2025Federated Unlearning Made Practical: Seamless Integration via Negated Pseudo-Gradients