As an emerging machine learning technique, federated learning has received significant attention recently due to its promising performance in mitigating privacy risks and costs. While most of the existing work of federated learning focused on designing learning algorithm to improve training performance, the incentive issue for encouraging users’ participation is still under-explored. This paper presents an analytical study on the server’s optimal incentive mechanism design, in the presence of users’ multi-dimensional private information (e.g., training cost and communication delay). Specifically, we consider a multi-dimensional contract-theoretic approach, with a key contribution of summarizing users’ multi-dimensional private information into a one-dimensional criterion that allows a complete order of users. We further perform the analysis in three information scenarios to reveal the impact of information asymmetry levels on server’s optimal strategy and minimum cost. We show that weakly incomplete information does not increase the server’s cost (comparing with the complete information scenario) when training data is IID, but it in general does when data is non-IID. Furthermore, the optimal mechanism design under strongly incomplete information is much more challenging, and it is not always optimal for the server to incentivize the group of users with the lowest training cost and delay to participate.

中文翻译：

---

多维隐私信息高效联邦学习的最优契约设计

作为一种新兴的机器学习技术，联邦学习因其在降低隐私风险和成本方面的良好表现而最近受到了广泛关注。虽然联邦学习的大部分现有工作都集中在设计学习算法以提高训练性能，但鼓励用户参与的激励问题仍未得到充分探索。本文对存在用户多维隐私信息（例如，训练成本和通信延迟）的服务器的最优激励机制设计进行了分析研究。具体来说，我们考虑了一种多维契约理论方法，其关键贡献是将用户的多维私人信息总结为一个允许用户完整订单的一维标准。我们进一步在三个信息场景中进行分析，以揭示信息不对称程度对服务器最优策略和最小成本的影响。我们表明，当训练数据为 IID 时，弱不完整信息不会增加服务器的成本（与完整信息场景相比），但通常在数据为非 IID 时会增加。此外，强不完整信息下的最优机制设计更具挑战性，服务器以最低的训练成本和延迟来激励一组用户参与并不总是最优的。我们表明，当训练数据为 IID 时，弱不完整信息不会增加服务器的成本（与完整信息场景相比），但通常在数据为非 IID 时会增加。此外，强不完整信息下的最优机制设计更具挑战性，服务器以最低的训练成本和延迟来激励一组用户参与并不总是最优的。我们表明，当训练数据为 IID 时，弱不完整信息不会增加服务器的成本（与完整信息场景相比），但通常在数据为非 IID 时会增加。此外，强不完整信息下的最优机制设计更具挑战性，服务器以最低的训练成本和延迟来激励一组用户参与并不总是最优的。