[论文解读] Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Jiawen Kang, Zehui Xiong+4 more|arXiv (Cornell University)|May 16, 2019

Privacy-Preserving Technologies in Data参考文献 20被引用 34

一句话总结

本论文利用契约理论设计激励机制，促使具备高质量数据的移动设备参与联邦学习，解决信息不对称与资源成本问题。通过 MNIST 实验展示学习效率的提升及可行性。

ABSTRACT

To strengthen data privacy and security, federated learning as an emerging machine learning technique is proposed to enable large-scale nodes, e.g., mobile devices, to distributedly train and globally share models without revealing their local data. This technique can not only significantly improve privacy protection for mobile devices, but also ensure good performance of the trained results collectively. Currently, most the existing studies focus on optimizing federated learning algorithms to improve model training performance. However, incentive mechanisms to motivate the mobile devices to join model training have been largely overlooked. The mobile devices suffer from considerable overhead in terms of computation and communication during the federated model training process. Without well-designed incentive, self-interested mobile devices will be unwilling to join federated learning tasks, which hinders the adoption of federated learning. To bridge this gap, in this paper, we adopt the contract theory to design an effective incentive mechanism for simulating the mobile devices with high-quality (i.e., high-accuracy) data to participate in federated learning. Numerical results demonstrate that the proposed mechanism is efficient for federated learning with improved learning accuracy.

研究动机与目标

• 在信息不对称下，激励具备高质量本地数据的移动设备加入联邦学习。
• 将数据质量建模为一种契约类型，并设计资源-奖励组合。
• 在保证数据所有者参与与诚信的前提下，最大化任务发布者的利润。

提出的方法

• 将联邦学习建模为一个垄断市场，包含任务发布者和数据所有者。
• 将数据质量定义为契约类型 p_theta_n，并形成契约包(R_n(f_n), f_n)。
• 施加个人理性（IR）和激励相容性（IC）约束，并转化为本地向下激励约束（LDIC）。
• 通过在时间和预算约束下，使用CVX求解凹优化问题，推导最优奖励R_n和CPU资源f_n。
• 证明通过求解松弛问题并强制单调性可得到可行契约，且比Stackelberg模型具有更高的发布者利润。

实验结果

研究问题

• RQ1 如何将契约理论应用于设计面对数据质量异质性的数据所有者在联邦学习中的激励？
• RQ2 数据质量（类型）和资源贡献对最优契约和整体系统利润有何影响？
• RQ3 在时间和预算约束下，是否能够在最大化任务发布者利润的同时满足IR和IC约束？

主要发现

• 基于契约的激励机制吸引了更高质量的数据并提升了联邦学习效率。
• 提出的契约能满足IR和IC约束，数据所有者仅选择他们指定的契约。
• 随着数据所有者类型的增加，发布者利润提升；契约模型下的利润比Stackelberg博弈模型更高。
• 提高本地数据精度的上限（高类型比例）会提高发布者利润。
• 所提方法的利润高于对称信息的Stackelberg基准，同时保持数据所有者效用非负。