Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries

Yuena Lin, Haichun Cai, Jun-Yi Hang, Haobo Wang, Zhen Yang, Gengyu Lyu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37745-37761, 2025.

Abstract

Graph contrastive learning (GCL) aims at narrowing positives while dispersing negatives, often causing a minority of samples with great similarities to gather as a small group. It results in two latent shortcomings in GCL: 1) local cohesion that a class cluster contains numerous independent small groups, and 2) global sparseness that these small groups (or isolated samples) dispersedly distribute among all clusters. These shortcomings make the learned distribution only focus on local similarities among partial samples, which hinders the ability to capture the ideal global structural properties among real clusters, especially high intra-cluster compactness and inter-cluster separateness. Considering this, we design a novel fuzzy boundary by extending the original cluster boundary with fuzzy set theory, which involves fuzzy boundary construction and fuzzy boundary contraction to address these shortcomings. The fuzzy boundary construction dilates the original boundaries to bridge the local groups, and the fuzzy boundary contraction forces the dispersed samples or groups within the fuzzy boundary to gather tightly, jointly mitigating local cohesion and global sparseness while forming the ideal global structural distribution. Extensive experiments demonstrate that a graph auto-encoder with the fuzzy boundary significantly outperforms current state-of-the-art GCL models in both downstream tasks and quantitative analysis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-lin25b, title = {Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries}, author = {Lin, Yuena and Cai, Haichun and Hang, Jun-Yi and Wang, Haobo and Yang, Zhen and Lyu, Gengyu}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {37745--37761}, 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/lin25b/lin25b.pdf}, url = {https://proceedings.mlr.press/v267/lin25b.html}, abstract = {Graph contrastive learning (GCL) aims at narrowing positives while dispersing negatives, often causing a minority of samples with great similarities to gather as a small group. It results in two latent shortcomings in GCL: 1) local cohesion that a class cluster contains numerous independent small groups, and 2) global sparseness that these small groups (or isolated samples) dispersedly distribute among all clusters. These shortcomings make the learned distribution only focus on local similarities among partial samples, which hinders the ability to capture the ideal global structural properties among real clusters, especially high intra-cluster compactness and inter-cluster separateness. Considering this, we design a novel fuzzy boundary by extending the original cluster boundary with fuzzy set theory, which involves fuzzy boundary construction and fuzzy boundary contraction to address these shortcomings. The fuzzy boundary construction dilates the original boundaries to bridge the local groups, and the fuzzy boundary contraction forces the dispersed samples or groups within the fuzzy boundary to gather tightly, jointly mitigating local cohesion and global sparseness while forming the ideal global structural distribution. Extensive experiments demonstrate that a graph auto-encoder with the fuzzy boundary significantly outperforms current state-of-the-art GCL models in both downstream tasks and quantitative analysis.} }
Endnote
%0 Conference Paper %T Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries %A Yuena Lin %A Haichun Cai %A Jun-Yi Hang %A Haobo Wang %A Zhen Yang %A Gengyu Lyu %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-lin25b %I PMLR %P 37745--37761 %U https://proceedings.mlr.press/v267/lin25b.html %V 267 %X Graph contrastive learning (GCL) aims at narrowing positives while dispersing negatives, often causing a minority of samples with great similarities to gather as a small group. It results in two latent shortcomings in GCL: 1) local cohesion that a class cluster contains numerous independent small groups, and 2) global sparseness that these small groups (or isolated samples) dispersedly distribute among all clusters. These shortcomings make the learned distribution only focus on local similarities among partial samples, which hinders the ability to capture the ideal global structural properties among real clusters, especially high intra-cluster compactness and inter-cluster separateness. Considering this, we design a novel fuzzy boundary by extending the original cluster boundary with fuzzy set theory, which involves fuzzy boundary construction and fuzzy boundary contraction to address these shortcomings. The fuzzy boundary construction dilates the original boundaries to bridge the local groups, and the fuzzy boundary contraction forces the dispersed samples or groups within the fuzzy boundary to gather tightly, jointly mitigating local cohesion and global sparseness while forming the ideal global structural distribution. Extensive experiments demonstrate that a graph auto-encoder with the fuzzy boundary significantly outperforms current state-of-the-art GCL models in both downstream tasks and quantitative analysis.
APA
Lin, Y., Cai, H., Hang, J., Wang, H., Yang, Z. & Lyu, G.. (2025). Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:37745-37761 Available from https://proceedings.mlr.press/v267/lin25b.html.

Related Material