期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 31, 期 7, 页码 2387-2397出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2019.2935608
关键词
Adaptation models; Data models; Neural networks; Predictive models; Nanoelectromechanical systems; Analytical models; Kernel; Distribution matching; domain adaptation; neural embedding; progressive learning; semisupervised learning
类别
资金
- National Natural Science Foundation of China [61822113, 41431175, 41871243, 61771349]
- Natural Science Foundation of Hubei Province [2018CFA050, 2018CFB432]
- National Key RAMP
- D Program of China [2018YFA0605501, 2018YFA0605503]
- Fundamental Research Funds for the Central Universities [2042018kf0206]
- Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant
- Canada Research Chairs Program
- National Post-Doctoral Program for Innovative Talents [BX20190250]
Domain adaptation aims to exploit the supervision knowledge in a source domain for learning prediction models in a target domain. In this article, we propose a novel representation learning-based domain adaptation method, i.e., neural embedding matching (NEM) method, to transfer information from the source domain to the target domain where labeled data is scarce. The proposed approach induces an intermediate common representation space for both domains with a neural network model while matching the embedding of data from the two domains in this common representation space. The embedding matching is based on the fundamental assumptions that a cross-domain pair of instances will be close to each other in the embedding space if they belong to the same class category, and the local geometry property of the data can be maintained in the embedding space. The assumptions are encoded via objectives of metric learning and graph embedding techniques to regularize and learn the semisupervised neural embedding model. We also provide a generalization bound analysis for the proposed domain adaptation method. Meanwhile, a progressive learning strategy is proposed and it improves the generalization ability of the neural network gradually. Experiments are conducted on a number of benchmark data sets and the results demonstrate that the proposed method outperforms several state-of-the-art domain adaptation methods and the progressive learning strategy is promising.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据