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.

本文研究了数据异质性下联邦去学习（FU）的多方面影响。我们引入了 FU 评估的关键指标，集中在验证、全局稳定性和局部公平性，并研究其内在的权衡。此外，我们通过优化框架对数据异质性下的去学习过程进行了形式化。我们的主要贡献在于对 FU 中的权衡进行了全面的理论分析，并揭示了数据异质性对 FU 的影响。利用这些见解，我们提出了管理权衡的 FU 机制，为 FU 机制的进一步发展提供指导。我们经验证实，我们的 FU 机制能有效平衡权衡，证实我们从理论分析中得出的见解。