.png){kind=icon}
.png){kind=icon}
Return
Anchor Graph Network for Incomplete Multiview Clustering
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2024.3349405.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Incomplete multiview clustering (IMVC) has received extensive attention in recent years. However, existing works still have several shortcomings: 1) some works ignore the correlation of sample pairs in the global structural distribution; 2) many methods are computational expensive, thus cannot be applicable to the large-scale incomplete data clustering tasks; and 3) some methods ignore the refinement of the bipartite graph structure. To address the above issues, we propose a novel anchor graph network for IMVC, which includes a generative model and a similarity metric network. Concretely, the method uses a generative model to construct bipartite graphs, which can mine latent global structure distributions of sample pairs. Later, we use graph convolution network (GCN) with the constructed bipartite graphs to learn the structural embeddings. Notably, the introduction of bipartite graphs can greatly reduce the computational complexity and thus enable our model to handle large-scale data. Unlike previous works based on bipartite graph, our method employs bipartite graphs to guide the learning process in GCNs. In addition, an innovative adaptive learning strategy that can construct robust bipartite graphs is incorporated into our method. Extensive experiments demonstrate that our method achieves the comparable or superior performance compared with the state-of-the-art methods.
Keywords:
Bipartite graph
Measurement
Learning systems
Feature extraction
Probability distribution
Data models
Convolution
Anchor graph
graph convolution network (GCN)
incomplete multiview data
multiview clustering
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W