论文标题
通过加权联合分布适应多源域的最佳运输
Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport
论文作者
论文摘要
使用来自多个标记源数据集的知识在未标记的目标数据集上适应域的问题正在变得越来越重要。一个关键的挑战是设计一种方法，可以克服源之间以及源和目标域之间的协变量和目标变化。在本文中，我们从新的角度解决了这个问题：我们没有在源域和目标域之间寻找潜在的表示不变，而是通过将其权重调整为手头的目标任务来利用源分布的多样性。我们的方法称为加权联合分配最佳运输（WJDOT），旨在同时找到源和目标分布之间的最佳基于运输的对齐，并重新对源分布进行重新加权。我们讨论了该方法的理论方面，并提出了一种概念上简单的算法。数值实验表明，所提出的方法在模拟和现实生活数据集上实现了最先进的性能。
The problem of domain adaptation on an unlabeled target dataset using knowledge from multiple labelled source datasets is becoming increasingly important. A key challenge is to design an approach that overcomes the covariate and target shift both among the sources, and between the source and target domains. In this paper, we address this problem from a new perspective: instead of looking for a latent representation invariant between source and target domains, we exploit the diversity of source distributions by tuning their weights to the target task at hand. Our method, named Weighted Joint Distribution Optimal Transport (WJDOT), aims at finding simultaneously an Optimal Transport-based alignment between the source and target distributions and a re-weighting of the sources distributions. We discuss the theoretical aspects of the method and propose a conceptually simple algorithm. Numerical experiments indicate that the proposed method achieves state-of-the-art performance on simulated and real-life datasets.
