Ambiguous Instance-Aware Contrastive Network with Multi-Level Matching for Multi-View Document Clustering
Zhenqiu Shu, Teng Sun, Yunwei Luo, Zhengtao Yu
Abstract
Multi-view document clustering (MvDC) aims to improve the accuracy and robustness of clustering by fully considering the complementarity of different views. However, in real-world clustering applications, most existing works suffer from the following challenges: 1) They primarily align multi-view data based on a single perspective, such as features and classes, thus ignoring the diversity and comprehensiveness of representations. 2) They treat each instance equally in cross-view contrastive learning without considering ambiguous ones, which weakens the model's discriminative ability. To address these problems, we propose an ambiguous instance-aware contrastive network with multi-level matching (AICN-MLM) for MvDC tasks. This model contains two key modules: a multi-level matching module and an ambiguous instance-aware contrastive learning module. The former attempts to align multi-view data from different perspectives, including features, pseudo-labels, and prototypes. The latter dynamically adjusts instance weights through a weight modulation function to highlight ambiguous instance pairs. Thus, our proposed method can effectively explore the consistency of multi-view document data and focus on ambiguous instances to enhance the model's discriminative ability. Extensive experimental results on several multi-view document datasets verify the effectiveness of our proposed method.
BibTeX
@article{Shu_Sun_Luo_Yu_2025, title={Ambiguous Instance-Aware Contrastive Network with Multi-Level Matching for Multi-View Document Clustering}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/34256}, DOI={10.1609/aaai.v39i19.34256}, abstractNote={Multi-view document clustering (MvDC) aims to improve the accuracy and robustness of clustering by fully considering the complementarity of different views. However, in real-world clustering applications, most existing works suffer from the following challenges: 1) They primarily align multi-view data based on a single perspective, such as features and classes, thus ignoring the diversity and comprehensiveness of representations. 2) They treat each instance equally in cross-view contrastive learning without considering ambiguous ones, which weakens the model’s discriminative ability. To address these problems, we propose an ambiguous instance-aware contrastive network with multi-level matching (AICN-MLM) for MvDC tasks. This model contains two key modules: a multi-level matching module and an ambiguous instance-aware contrastive learning module. The former attempts to align multi-view data from different perspectives, including features, pseudo-labels, and prototypes. The latter dynamically adjusts instance weights through a weight modulation function to highlight ambiguous instance pairs. Thus, our proposed method can effectively explore the consistency of multi-view document data and focus on ambiguous instances to enhance the model’s discriminative ability. Extensive experimental results on several multi-view document datasets verify the effectiveness of our proposed method.}, number={19}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Shu, Zhenqiu and Sun, Teng and Luo, Yunwei and Yu, Zhengtao}, year={2025}, month={Apr.}, pages={20479-20487} }