Many problems in machine learning rely on multi-task learning (MTL), in which
the goal is to solve multiple related machine learning tasks simultaneously.
MTL is particularly relevant for privacy-sensitive applications in areas such
as healthcare, finance, and IoT computing, where sensitive data from multiple,
varied sources are shared for the purpose of learning. In this work, we
formalize notions of client-level privacy for MTL via joint differential
privacy (JDP), a relaxation of differential privacy for mechanism design and
distributed optimization. We then propose an algorithm for mean-regularized
MTL, an objective commonly used for applications in personalized federated
learning, subject to JDP. We analyze our objective and solver, providing
certifiable guarantees on both privacy and utility. Empirically, we find that
our method provides improved privacy/utility trade-offs relative to global
baselines across common federated learning benchmarks.

本研究中，我们通过联合差分隐私 (JDP) 对客户级隐私概念进行了形式化，提出了一种算法用于在联邦学习应用中常用的均值正则化多任务学习 (MTL)，并对其进行了分析，得到了隐私和效用方面的可证明保证。实证研究表明，相对于全局基线，我们的方法在常见的联邦学习基准测试中提供了更好的隐私 / 效用权衡。