arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.12938cs.LGstat.ML
收藏

基于加权联合分布最优传输的多源领域自适应

Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport

University of Genova(热那亚大学);Istituto Italiano di Tecnologia(意大利理工学院);École Polytechnique(巴黎综合理工学院);Institut Polytechnique de Paris(巴黎理工学院);Criteo AI Lab(科韬人工智能实验室);University College London(伦敦大学学院)

Rosanna Turrisi, Rémi Flamary, Alain Rakotomamonjy, Massimiliano Pontil

摘要:

利用来自多个标记源数据集的知识对未标记目标数据集进行领域自适应的问题变得越来越重要。一个关键的挑战是设计一种方法,克服了协变量和目标转移之间的源,源和目标域。在本文中,我们从一个新的角度来解决这个问题:而不是寻找源和目标域之间的一个潜在的表示不变,我们利用源分布的多样性,调整其权重的目标任务在手。我们的方法,名为加权联合分布最优运输(WJDOT),旨在同时找到一个最优的运输为基础的对齐源和目标分布和重新加权的源分布。我们讨论了该方法的理论方面,并提出了一个概念上简单的算法。数值实验表明,所提出的方法实现了最先进的性能在模拟和现实生活中的数据集。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑