Federated Unlearning: a Perspective of Stability and Fairness
CoRR(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要