通过激励机制缓解联邦遗忘中数据异构带来的副作用。
Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentives
- 将联邦遗忘建模为斯塔克尔伯格博弈，服务器以支付激励关键客户留任。
- 在非独立同分布场景下，系统稳定性提升6.23%，最差客户端性能下降减少10.05%。
- 适合关注联邦学习长期稳定性和隐私保护的系统设计者。
联邦遗忘（Federated Unlearning, FU）可移除特定客户端对训练模型的影响。但在非独立同分布（non-IID）设置下，移除客户端会引发严重副作用：与被移除者数据分布相似的剩余客户端面临不成比例的性能下降，且全局模型稳定性恶化。这些脆弱客户端因此降低留任意愿，可能引发连锁退出，进一步破坏系统。为此，我们建立理论框架，量化数据异构性对遗忘效果的影响。基于此，将FU建模为斯塔克尔伯格博弈，服务器根据客户端对遗忘效率与系统稳定性的贡献，战略性地提供补偿以保留关键成员。严格的均衡分析揭示了数据异构性如何根本性影响全局目标与客户端利益之间的权衡。实验表明，该方法使全局稳定性提升最高达6.23%，最坏情况下的客户端性能下降减少10.05%，运行效率相比完整重训练最高提升38.6%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。