mlsanityData to 7 Oct 2026

Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentives

arXiv 2410.15045 ↗First posted 19 Oct 2024cs.GT cs.AIcited by 0

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

Abstract (arXiv)

Federated Unlearning (FU) enables the removal of specific clients' data influence from trained models. However, in non-IID settings, removing clients creates critical side effects: remaining clients with similar data distributions suffer disproportionate performance degradation, while the global model's stability deteriorates. These vulnerable clients then have reduced incentives to stay in the federation, potentially triggering a cascade of withdrawals that further destabilize the system. To address this challenge, we develop a theoretical framework that quantifies how data heterogeneity impacts unlearning outcomes. Based on these insights, we model FU as a Stackelberg game where the server strategically offers payments to retain crucial clients based on their contribution to both unlearning effectiveness and system stability. Our rigorous equilibrium analysis reveals how data heterogeneity fundamentally shapes the trade-offs between system-wide objectives and client interests. Our approach improves global stability by up to 6.23%, reduces worst-case client degradation by 10.05%, and achieves up to 38.6% runtime efficiency over complete retraining.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 15 of its 38 references that are in the map. First posted on arXiv 19 Oct 2024.

Builds on

15 of 38 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Federated Unlearning: a Perspective of Stability and Fairness2 Feb
  2. 2023QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation27 Nov
  3. 2023FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning19 Sep
  4. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning4 Feb
  5. 2022SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization21 Nov
  6. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar

Other references · 9

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  4. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  5. 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
  6. 2023Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participationcited by 8
  7. 2023Strategic Data Revocation in Federated Unlearningcited by 5
  8. 2023Joint Participation Incentive and Network Pricing Design for Federated Learningcited by 4
  9. 2024Guaranteeing Data Privacy in Federated Unlearning with Dynamic User Participationcited by 4

Built on by

Not cited yet.