mlsanityData to 7 Oct 2026

Federated Unlearning: a Perspective of Stability and Fairness

arXiv 2402.01276 ↗First posted 2 Feb 2024cs.AIcited by 7

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

Abstract (arXiv)

This paper explores the multifaceted consequences of federated unlearning (FU) with data heterogeneity. We introduce key metrics for FU assessment, concentrating on verification, global stability, and local fairness, and investigate the inherent trade-offs. Furthermore, we formulate the unlearning process with data heterogeneity through an optimization framework. Our key contribution lies in a comprehensive theoretical analysis of the trade-offs in FU and provides insights into data heterogeneity's impacts on FU. Leveraging these insights, we propose FU mechanisms to manage the trade-offs, guiding further development for FU mechanisms. We empirically validate that our FU mechanisms effectively balance trade-offs, confirming insights derived from our theoretical analysis.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 31 of its 56 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

31 of 56 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directions31 Oct
  2. 2022Machine Unlearning of Federated Clusters28 Oct
  3. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?12 Jul
  4. 2022VeriFi: Towards Verifiable Federated Unlearning25 May
  5. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
  6. 2022Federated Unlearning with Knowledge Distillation24 Jan

Other references · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2019Machine Unlearningcited by 1,020
  6. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  7. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  8. 2018A Reductions Approach to Fair Classificationcited by 585
  9. 2019Certified Data Removal from Machine Learning Modelscited by 512
  10. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  11. 2019Agnostic Federated Learningcited by 451
  12. 2019Fair Resource Allocation in Federated Learningcited by 389
13 more
  1. 2021A Field Guide to Federated Optimizationcited by 312
  2. 2022A Survey of Machine Unlearningcited by 298
  3. 2021Fast Yet Effective Machine Unlearningcited by 209
  4. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  5. 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
  6. 2022Continual Learning and Private Unlearningcited by 124
  7. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
  8. 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
  9. 2020Free-rider Attacks on Model Aggregation in Federated Learningcited by 57
  10. 2021Towards Fairness-Aware Federated Learningcited by 57
  11. 2022Deep Regression Unlearningcited by 32
  12. 2020Federated Unlearningcited by 27
  13. 2022Fair Federated Learning via Bounded Group Losscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 1.

7 papers.

  1. 2024Threats, Attacks, and Defenses in Machine Unlearning: A Surveycited by 34
  2. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  3. 2024Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgottencited by 3
  4. 2025NOVO: Unlearning-Compliant Vision Transformerscited by 2
  5. 2024A Survey on Federated Unlearning: Challenges and Opportunitiescited by 0
  6. 2024Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentivescited by 0
  7. 2026Rethinking Federated Unlearning via the Lens of Memorizationcited by 0