Incentive Mechanism Design for Federated Learning and Unlearning
Incentive Mechanism Design for Federated Learning and Unlearning
复制标题
DOI：
10.1145/3565287.3610269
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Ningning Ding;Zhenyu Sun;Ermin Wei;Randall Berry
中科院分区：
文献类型：
--
作者：
Ningning Ding;Zhenyu Sun;Ermin Wei;Randall Berry
为保护联邦学习中用户的被遗忘权，联邦遗忘旨在消除离开用户的数据对全局学习模型的影响。当前联邦遗忘的研究主要集中在开发有效且高效的遗忘技术上。然而，激励有价值的用户保持参与并防止其数据被遗忘的问题仍未得到充分探索，但对遗忘模型的性能至关重要。本文聚焦于激励问题，并为联邦学习和遗忘开发了一种激励机制。我们首先描述了离开用户对全局模型准确性的影响以及遗忘所需的通信轮数。基于这些结果，我们提出了一个四阶段博弈来捕捉学习和遗忘过程中的交互和信息更新。一个关键贡献是将用户的多维私有信息总结为一维指标以指导激励设计。我们表明，成本高且经历显著训练损失的用户更有可能通过联邦遗忘停止参与。服务器倾向于保留对模型有重大贡献的用户，但会在用户的训练损失上进行权衡，因为保留用户的大量训练损失会增加隐私成本但会降低遗忘成本。数值结果证明了遗忘激励对于保留有价值的离开用户的必要性，并且还表明与现有基准相比，我们提出的机制将服务器成本降低了多达53.91%。
To protect users' right to be forgotten in federated learning, federated unlearning aims at eliminating the impact of leaving users' data on the global learned model. The current research in federated unlearning mainly concentrated on developing effective and efficient unlearning techniques. However, the issue of incentivizing valuable users to remain engaged and preventing their data from being unlearned is still under-explored, yet important to the unlearned model performance. This paper focuses on the incentive issue and develops an incentive mechanism for federated learning and unlearning. We first characterize the leaving users' impact on the global model accuracy and the required communication rounds for unlearning. Building on these results, we propose a four-stage game to capture the interaction and information updates during the learning and unlearning process. A key contribution is to summarize users' multi-dimensional private information into one-dimensional metrics to guide the incentive design. We show that users who incur high costs and experience significant training losses are more likely to discontinue their engagement through federated unlearning. The server tends to retain users who make substantial contributions to the model but has a trade-off on users' training losses, as large training losses of retained users increase privacy costs but decrease unlearning costs. The numerical results demonstrate the necessity of unlearning incentives for retaining valuable leaving users, and also show that our proposed mechanisms decrease the server's cost by up to 53.91% compared to state-of-the-art benchmarks.