Assisted Unsupervised Domain Adaptation
Assisted Unsupervised Domain Adaptation
复制标题
DOI：
10.1109/isit54713.2023.10206737
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Cheng Chen;Jiawei Zhang;Jie Ding;Yi Zhou
中科院分区：
文献类型：
--
作者：
Cheng Chen;Jiawei Zhang;Jie Ding;Yi Zhou
无监督域适应（UDA）是一种流行的机器学习技术，它允许人们根据从不同域收集的各种数据来训练模型。然而，这种技术要求学习者收集大量正确标记的数据样本，这在许多应用中可能成本高昂且不现实。在这项工作中，我们为 UDA 提出了一个去中心化的辅助学习框架。在这个框架中，学习器只有从某个源域收集的有限数量的标记数据样本，其目标是训练目标域的分类器。为了提高域适应性能，它通过与外部服务提供商交互来寻求帮助，外部服务提供商拥有从相关源域收集的许多标记数据样本。我们开发了一种辅助 UDA 算法，可以避免数据共享，并且可以在几轮交互内显着提高学习器的领域适应性能。在基准数据集上使用深度神经网络的实验证明了该算法的有效性。
Unsupervised domain adaptation (UDA) is a popular machine learning technique that allows one to train models over diverse data collected from different domains. However, this technique requires the learner to collect a large number of properly labeled data samples, which can be costly and unrealistic in many applications. In this work, we propose a decentralized assisted learning framework for UDA. In this framework, a learner has only a limited number of labeled data samples collected from a certain source domain and aims to train a classifier for the target domain. To improve domain adaptation performance, it seeks assistance by interacting with an external service provider, who possesses many labeled data samples collected from a related source domain. We develop an assisted UDA algorithm that avoids data sharing and can significantly improve the learner’s domain adaptation performance within a few rounds of interaction. Experiments using deep neural networks on benchmark datasets demonstrate the effectiveness of this algorithm.