AMCFCN: attentive multi-view contrastive fusion clustering net

Author:

Xiao Huarun1,Hong Zhiyong1,Xiong Liping1,Zeng Zhiqiang1

Affiliation:

1. College of Electronic and Information Engineering, Wuyi University, Jiangmen, Guangdong, China

Abstract

Advances in deep learning have propelled the evolution of multi-view clustering techniques, which strive to obtain a view-common representation from multi-view datasets. However, the contemporary multi-view clustering community confronts two prominent challenges. One is that view-specific representations lack guarantees to reduce noise introduction, and another is that the fusion process compromises view-specific representations, resulting in the inability to capture efficient information from multi-view data. This may negatively affect the accuracy of the clustering results. In this article, we introduce a novel technique named the “contrastive attentive strategy” to address the above problems. Our approach effectively extracts robust view-specific representations from multi-view data with reduced noise while preserving view completeness. This results in the extraction of consistent representations from multi-view data while preserving the features of view-specific representations. We integrate view-specific encoders, a hybrid attentive module, a fusion module, and deep clustering into a unified framework called AMCFCN. Experimental results on four multi-view datasets demonstrate that our method, AMCFCN, outperforms seven competitive multi-view clustering methods. Our source code is available at https://github.com/xiaohuarun/AMCFCN.

Funder

National Natural Science Foundation of China

Guangdong University Scientific Research Project, China

Joint Research and Development Fund of Wuyi University and Hong Kong and Macau

Publisher

PeerJ

Reference39 articles.

1. Deep multimodal subspace clustering networks;Abavisani;Journal of IEEE Selected Topics in Signal Processing,2018

2. Diversity-induced multi-view subspace clustering;Cao,2015

3. Deep clustering for unsupervised learning of visual features;Caron,2018

4. Multi-view clustering in latent embedding space;Chen;Proceedings of the AAAI Conference on Artificial Intelligence,2020

5. A simple framework for contrastive learning of visual representations;Chen,2020

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3