提出函数追踪方法，在联邦学习中实现全局群体公平性。
Global Group Fairness in Federated Learning via Function Tracking
- 用最大均值差异函数追踪全局公平正则项，通信开销小。
- 在FedAvg框架下保持收敛性，理论与实验均验证有效。
- 适合关注公平性与隐私保护的联邦学习研究者。
我们研究联邦学习中的群体公平性正则化，目标是在分布式环境下训练一个全局公平的模型。分布式训练中确保全局公平面临独特挑战，因为公平性正则化通常涉及所有客户端间分布的概率度量，且无法自然按客户端分离。为此，我们基于最大均值差异（MMD）提出一种函数追踪方案，通信开销小。该方案可无缝集成至多数联邦学习算法，并在FedAvg框架下保持严格的收敛保证。此外，当引入差分隐私时，基于核的MMD正则化可通过核变换进行直观分析，具有清晰的核卷积解释。数值实验验证了理论结论。
原文摘要 · Abstract (English)
We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probability metrics between distributions across all clients and are not naturally separable by client. To address this, we introduce a function-tracking scheme for the global fairness regularizer based on a Maximum Mean Discrepancy (MMD), which incurs a small communication overhead. This scheme seamlessly integrates into most federated learning algorithms while preserving rigorous convergence guarantees, as demonstrated in the context of FedAvg. Additionally, when enforcing differential privacy, the kernel-based MMD regularization enables straightforward analysis through a change of kernel, leveraging an intuitive interpretation of kernel convolution. Numerical experiments confirm our theoretical insights.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。