论文标题
跨域和设备学习：聚类联合学习中的无源域的适应性
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
论文作者
论文摘要
联邦学习（FL）最近成为解决现实世界语义细分（SS）中域转移的一种可能方法，而不会损害收集的数据的私人性质。但是，大多数现有的作品不切实际地假定远程客户端中的标记数据。在这里，我们提出了一个新的任务（FFREEDA），其中未标记客户的数据，并且服务器仅访问源标记的数据集以进行预训练。为了解决FFREEDA，我们提出了LADD，该LADD通过采用自我训练的方式使用临时正规化技术来利用预培训的模型的知识，并根据客户的风格引入了一种新颖的联邦聚集聚合计划。我们的实验表明，我们的算法能够有效地应对新任务的表现优于现有方法。该代码可在https://github.com/erosinho13/ladd上找到。
Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data. However, most of the existing works on FL unrealistically assume labeled data in the remote clients. Here we propose a novel task (FFREEDA) in which the clients' data is unlabeled and the server accesses a source labeled dataset for pre-training only. To solve FFREEDA, we propose LADD, which leverages the knowledge of the pre-trained model by employing self-supervision with ad-hoc regularization techniques for local training and introducing a novel federated clustered aggregation scheme based on the clients' style. Our experiments show that our algorithm is able to efficiently tackle the new task outperforming existing approaches. The code is available at https://github.com/Erosinho13/LADD.
