Graph Contrastive Partial Multi-View Clustering

Yiming Wang

doi:10.1109/TMM.2022.3210376

2023-01-01

PRE

Yiming Wang

常

常冬霞 (Dongxia Chang) *

DOI：10.1109/TMM.2022.3210376

原文链接

原文求助

摘要

En 中文

With the diversity of information acquisition, data is stored and transmitted in an increasing number of modalities. Nevertheless, it is not unusual for parts of the data to be lost in some views due to unavoidable acquisition, transmission or storage errors. In this paper, we propose an augmentation-free graph contrastive learning framework to solve the problem of partial multi-view clustering. Notably, we suppose that the representations of similar samples (i.e., belonging to the same cluster) should be similar. This is distinct from the general unsupervised contrastive learning that assumes an image and its augmentations share a similar representation. Specifically, relation graphs are constructed using the nearest neighbors to identify existing similar samples, then the constructed inter-instance relation graphs are transferred to the missing views to build graphs on the corresponding missing data. Subsequently, two main components, within-view graph contrastive learning and cross-view graph consistency learning, are devised to maximize the mutual information of different views within a cluster. The proposed approach elevates instance-level contrastive learning and missing data inference to the cluster-level, effectively mitigating the impact of individual missing data on clustering. Experiments on several challenging datasets demonstrate the superiority of our proposed methods.

Keyword:

Kernel

Clustering methods

Generative adversarial networks

Task analysis

Semantics

Representation learning

Media

Contrastive learning

multi-view learning

partial multi-view clustering