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

arXiv: https://arxiv.org/abs/2410.15045 · HTML: https://mlsanity.com/paper/2410.15045/

## 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 15 of its 38 references that are in the map.
- First posted on arXiv 19 Oct 2024.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning](https://mlsanity.com/paper/1812.00535/) (2018)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling](https://mlsanity.com/paper/2112.11256/) (2021)
- [Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning](https://mlsanity.com/paper/2302.02069/) (2023)
- [SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization](https://mlsanity.com/paper/2211.11656/) (2022)
- [FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning](https://mlsanity.com/paper/2309.10283/) (2023)
- [QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation](https://mlsanity.com/paper/2311.15603/) (2023)
- [Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation](https://mlsanity.com/paper/2304.07981/) (2023)
- [Strategic Data Revocation in Federated Unlearning](https://mlsanity.com/paper/2312.01235/) (2023)
- [Federated Unlearning: a Perspective of Stability and Fairness](https://mlsanity.com/paper/2402.01276/) (2024)
- [Joint Participation Incentive and Network Pricing Design for Federated Learning](https://mlsanity.com/paper/2309.16712/) (2023)
- [Guaranteeing Data Privacy in Federated Unlearning with Dynamic User Participation](https://mlsanity.com/paper/2406.00966/) (2024)

## 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.