Disentangling Homophily and Heterophily in Multimodal Graph Clustering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916852985233408 |
|---|---|
| author | Guo, Zhaochen Shen, Zhixiang Xie, Xuanting Wen, Liangjian Kang, Zhao |
| author_facet | Guo, Zhaochen Shen, Zhixiang Xie, Xuanting Wen, Liangjian Kang, Zhao |
| contents | Multimodal graphs, which integrate unstructured heterogeneous data with structured interconnections, offer substantial real-world utility but remain insufficiently explored in unsupervised learning. In this work, we initiate the study of multimodal graph clustering, aiming to bridge this critical gap. Through empirical analysis, we observe that real-world multimodal graphs often exhibit hybrid neighborhood patterns, combining both homophilic and heterophilic relationships. To address this challenge, we propose a novel framework -- \textsc{Disentangled Multimodal Graph Clustering (DMGC)} -- which decomposes the original hybrid graph into two complementary views: (1) a homophily-enhanced graph that captures cross-modal class consistency, and (2) heterophily-aware graphs that preserve modality-specific inter-class distinctions. We introduce a \emph{Multimodal Dual-frequency Fusion} mechanism that jointly filters these disentangled graphs through a dual-pass strategy, enabling effective multimodal integration while mitigating category confusion. Our self-supervised alignment objectives further guide the learning process without requiring labels. Extensive experiments on both multimodal and multi-relational graph datasets demonstrate that DMGC achieves state-of-the-art performance, highlighting its effectiveness and generalizability across diverse settings. Our code is available at https://github.com/Uncnbb/DMGC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15253 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Disentangling Homophily and Heterophily in Multimodal Graph Clustering Guo, Zhaochen Shen, Zhixiang Xie, Xuanting Wen, Liangjian Kang, Zhao Artificial Intelligence Machine Learning Social and Information Networks Multimodal graphs, which integrate unstructured heterogeneous data with structured interconnections, offer substantial real-world utility but remain insufficiently explored in unsupervised learning. In this work, we initiate the study of multimodal graph clustering, aiming to bridge this critical gap. Through empirical analysis, we observe that real-world multimodal graphs often exhibit hybrid neighborhood patterns, combining both homophilic and heterophilic relationships. To address this challenge, we propose a novel framework -- \textsc{Disentangled Multimodal Graph Clustering (DMGC)} -- which decomposes the original hybrid graph into two complementary views: (1) a homophily-enhanced graph that captures cross-modal class consistency, and (2) heterophily-aware graphs that preserve modality-specific inter-class distinctions. We introduce a \emph{Multimodal Dual-frequency Fusion} mechanism that jointly filters these disentangled graphs through a dual-pass strategy, enabling effective multimodal integration while mitigating category confusion. Our self-supervised alignment objectives further guide the learning process without requiring labels. Extensive experiments on both multimodal and multi-relational graph datasets demonstrate that DMGC achieves state-of-the-art performance, highlighting its effectiveness and generalizability across diverse settings. Our code is available at https://github.com/Uncnbb/DMGC. |
| title | Disentangling Homophily and Heterophily in Multimodal Graph Clustering |
| topic | Artificial Intelligence Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2507.15253 |