Multi-View Graph Clustering via Node-Guided Contrastive Encoding

Yazhou Ren, Junlong Ke, Zichen Wen, Tianyi Wu, Yang Yang, Xiaorong Pu, Lifang He
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51421-51435, 2025.

Abstract

Multi-view clustering has gained significant attention for integrating multi-view information in multimedia applications. With the growing complexity of graph data, multi-view graph clustering (MVGC) has become increasingly important. Existing methods primarily use Graph Neural Networks (GNNs) to encode structural and feature information, but applying GNNs within contrastive learning poses specific challenges, such as integrating graph data with node features and handling both homophilic and heterophilic graphs. To address these challenges, this paper introduces Node-Guided Contrastive Encoding (NGCE), a novel MVGC approach that leverages node features to guide embedding generation. NGCE enhances compatibility with GNN filtering, effectively integrates homophilic and heterophilic information, and strengthens contrastive learning across views. Extensive experiments demonstrate its robust performance on six homophilic and heterophilic multi-view benchmark datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-ren25a, title = {Multi-View Graph Clustering via Node-Guided Contrastive Encoding}, author = {Ren, Yazhou and Ke, Junlong and Wen, Zichen and Wu, Tianyi and Yang, Yang and Pu, Xiaorong and He, Lifang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {51421--51435}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/ren25a/ren25a.pdf}, url = {https://proceedings.mlr.press/v267/ren25a.html}, abstract = {Multi-view clustering has gained significant attention for integrating multi-view information in multimedia applications. With the growing complexity of graph data, multi-view graph clustering (MVGC) has become increasingly important. Existing methods primarily use Graph Neural Networks (GNNs) to encode structural and feature information, but applying GNNs within contrastive learning poses specific challenges, such as integrating graph data with node features and handling both homophilic and heterophilic graphs. To address these challenges, this paper introduces Node-Guided Contrastive Encoding (NGCE), a novel MVGC approach that leverages node features to guide embedding generation. NGCE enhances compatibility with GNN filtering, effectively integrates homophilic and heterophilic information, and strengthens contrastive learning across views. Extensive experiments demonstrate its robust performance on six homophilic and heterophilic multi-view benchmark datasets.} }
Endnote
%0 Conference Paper %T Multi-View Graph Clustering via Node-Guided Contrastive Encoding %A Yazhou Ren %A Junlong Ke %A Zichen Wen %A Tianyi Wu %A Yang Yang %A Xiaorong Pu %A Lifang He %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-ren25a %I PMLR %P 51421--51435 %U https://proceedings.mlr.press/v267/ren25a.html %V 267 %X Multi-view clustering has gained significant attention for integrating multi-view information in multimedia applications. With the growing complexity of graph data, multi-view graph clustering (MVGC) has become increasingly important. Existing methods primarily use Graph Neural Networks (GNNs) to encode structural and feature information, but applying GNNs within contrastive learning poses specific challenges, such as integrating graph data with node features and handling both homophilic and heterophilic graphs. To address these challenges, this paper introduces Node-Guided Contrastive Encoding (NGCE), a novel MVGC approach that leverages node features to guide embedding generation. NGCE enhances compatibility with GNN filtering, effectively integrates homophilic and heterophilic information, and strengthens contrastive learning across views. Extensive experiments demonstrate its robust performance on six homophilic and heterophilic multi-view benchmark datasets.
APA
Ren, Y., Ke, J., Wen, Z., Wu, T., Yang, Y., Pu, X. & He, L.. (2025). Multi-View Graph Clustering via Node-Guided Contrastive Encoding. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:51421-51435 Available from https://proceedings.mlr.press/v267/ren25a.html.

Related Material