Modern machine learning (ML) models have grown to a scale where training them on a single machine becomes impractical. As a result, there is a growing trend to leverage federated learning (FL) techniques to train large ML models in a distributed and collaborative manner. These models, however, when deployed on new devices, might struggle to generalize well due to domain shifts. In this context, federated domain adaptation (FDA) emerges as a powerful approach to address this challenge. Most existing FDA approaches typically focus on aligning the distributions between source and target domains by minimizing their (e.g., MMD) distance. Such strategies, however, inevitably introduce high communication overheads and can be highly sensitive to network reliability. In this paper, we introduce RF-TCA, an enhancement to the standard Transfer Component Analysis approach that significantly accelerates computation without compromising theoretical and empirical performance. Leveraging the computational advantage of RF-TCA, we further extend it to FDA setting with FedRF-TCA. The proposed FedRF-TCA protocol boasts communication complexity that is \emph{independent} of the sample size, while maintaining performance that is either comparable to or even surpasses state-of-the-art FDA methods. We present extensive experiments to showcase the superior performance and robustness (to network condition) of FedRF-TCA.

翻译：现代机器学习模型的规模已经增长到在单台机器上训练不切实际的程度。因此，利用联邦学习技术在分布式协作方式下训练大型机器学习模型的趋势日益增长。然而，这些模型部署到新设备上时，可能因域偏移而难以良好泛化。在此背景下，联邦域适应成为应对该挑战的有效方法。现有大多数联邦域适应方法通常通过最小化源域与目标域之间的（例如MMD）距离来对齐其分布。然而，此类策略不可避免地会引入高通信开销，且对网络可靠性极为敏感。本文提出RF-TCA方法，这是对标准迁移成分分析方法的增强，在不牺牲理论和实证性能的前提下显著加速计算。利用RF-TCA的计算优势，我们进一步将其扩展至联邦域适应场景，提出FedRF-TCA协议。所提出的FedRF-TCA协议的通信复杂度与样本量无关，同时保持与现有最优联邦域适应方法相当甚至更优的性能。我们通过大量实验展示了FedRF-TCA在（网络条件下的）优越性能和鲁棒性。