On deep unsupervised active learning

Changsheng Li, Handong Ma, Zhao Kang, Ye Yuan, Xiao Yu Zhang, Guoren Wang*

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

19 引用 (Scopus)

摘要

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating. Most existing works are based on shallow linear models by assuming that each sample can be well approximated by the span (i.e., the set of all linear combinations) of certain selected samples, and then take these selected samples as representative ones to label. However, in practice, the data do not necessarily conform to linear models, and how to model nonlinearity of data often becomes the key point to success. In this paper, we present a novel Deep neural network framework for Unsupervised Active Learning, called DUAL. DUAL can explicitly learn a nonlinear embedding to map each input into a latent space through an encoder-decoder architecture, and introduce a selection block to select representative samples in the the learnt latent space. In the selection block, DUAL considers to simultaneously preserve the whole input patterns as well as the cluster structure of data. Extensive experiments are performed on six publicly available datasets, and experimental results clearly demonstrate the efficacy of our method, compared with state-of-the-arts.

源语言英语
主期刊名Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020
编辑Christian Bessiere
出版商International Joint Conferences on Artificial Intelligence
2626-2632
页数7
ISBN(电子版)9780999241165
出版状态已出版 - 2020
活动29th International Joint Conference on Artificial Intelligence, IJCAI 2020 - Yokohama, 日本
期限: 1 1月 2021 → …

出版系列

姓名IJCAI International Joint Conference on Artificial Intelligence
2021-January
ISSN(印刷版)1045-0823

会议

会议29th International Joint Conference on Artificial Intelligence, IJCAI 2020
国家/地区日本
Yokohama
时期1/01/21 → …

指纹

探究 'On deep unsupervised active learning' 的科研主题。它们共同构成独一无二的指纹。

引用此