计算机科学
杠杆(统计)
瓶颈
聚类分析
人工智能
融合
代表(政治)
信息瓶颈法
透视图(图形)
任务(项目管理)
机器学习
数据挖掘
自然语言处理
管理
政治
政治学
法学
经济
嵌入式系统
哲学
语言学
作者
Guanzhou Ke,Zhiyong Hong,Zhiqiang Zeng,Zeyi Liu,Yangjie Sun,Yannan Xie
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2021-12-15
卷期号:: 653-660
被引量:86
标识
DOI:10.1109/bigdata52589.2021.9671851
摘要
With the development of big data, deep learning has made remarkable progress on multi-view clustering. Multi-view fusion is a crucial technique for the model obtaining a common representation. However, existing literature adopts shallow fusion strategies, such as weighted-sum fusion and concatenating fusion, which fail to capture complex information from multiple views. In this paper, we propose a novel fusion technique, entitled contrastive fusion, which can extract consistent representations from multiple views and maintain the characteristic of view-specific representations. Specifically, we study multi-view alignment from an information bottleneck perspective and introduce an intermediate variable to align each view-specific representation. Furthermore, we leverage a single-view clustering method as a predictive task to ensure the contrastive fusion is working. We integrate all components into an unified framework called CONtrAstive fusion Network (CONAN). Experiment results on five multi-view datasets demonstrate that CONAN outperforms state-of-the-art methods. Our source code will be available soon at https://github.com/guanzhou-ke/conan.
科研通智能强力驱动
Strongly Powered by AbleSci AI