计算机科学与探索2025，Vol.19Issue(8)：2085-2098,14.DOI:10.3778/j.issn.1673-9418.2410086
融合局部和全局特征的深度多视图聚类网络
Deep Multi-view Clustering Network Integrating Local and Global Features
摘要
Abstract
Multiview clustering is an important research direction in data analysis,aiming to enhance clustering accuracy by integrating data from different perspectives.However,traditional multiview clustering methods improve clustering per-formance to some extent but often overlook the interaction and fusion of local and global features among views.More-over,recent multiview deep clustering methods,which enhance representation capabilities through deep neural networks or contrastive learning,focus on local or global features,failing to integrate these two types of features within the same framework.To address these shortcomings,this paper proposes a deep multiview clustering model that integrates convolu-tional neural networks and Transformers(deep multi-view clustering network integrating local and global features,DMVCN-ILGF).The model designs parallel convolutional and Transformer branches to extract local and global features,respectively.To achieve effective feature fusion,the model introduces a feature interaction mechanism(FIM)and a fea-ture fusion module(FFM),which fully integrates feature information from various views to enhance the interaction and fu-sion of different features,improving clustering performance.Additionally,instance-level and category-level contrastive losses are designed to compute the similarity between local and global features across views,optimizing the model's repre-sentation capabilities and clustering outcomes.Experimental results demonstrate that the DMVCN-ILGF model signifi-cantly outperforms existing methods across multiple multiview datasets in clustering performance.关键词
多视图聚类/卷积神经网络/Transformer/特征融合Key words
multi-view clustering/convolutional neural networks/Transformer/feature fusion分类
信息技术与安全科学引用本文复制引用
李顺勇,李嘉茗,曹付元,郑孟蛟..融合局部和全局特征的深度多视图聚类网络[J].计算机科学与探索,2025,19(8):2085-2098,14.基金项目
国家自然科学基金(62376145,82274360) （62376145,82274360）
山西省基础研究计划(202303021221054) （202303021221054）
山西省回国留学人员科研资助项目(2024-002).This work was supported by the National Natural Science Foundation of China(62376145,82274360),the Fundamental Research Pro-gram of Shanxi Province(202303021221054),and the Research Project Supported by Shanxi Scholarship Council of China(2024-002). （2024-002）
