Dual-Center Graph Clustering with Neighbor Distribution

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cheng, Enhao, Zhang, Shoujia, Yin, Jianhua, Jin, Li, Nie, Liqiang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916849809096704
author Cheng, Enhao
Zhang, Shoujia
Yin, Jianhua
Jin, Li
Nie, Liqiang
author_facet Cheng, Enhao
Zhang, Shoujia
Yin, Jianhua
Jin, Li
Nie, Liqiang
contents Graph clustering is crucial for unraveling intricate data structures, yet it presents significant challenges due to its unsupervised nature. Recently, goal-directed clustering techniques have yielded impressive results, with contrastive learning methods leveraging pseudo-label garnering considerable attention. Nonetheless, pseudo-label as a supervision signal is unreliable and existing goal-directed approaches utilize only features to construct a single-target distribution for single-center optimization, which lead to incomplete and less dependable guidance. In our work, we propose a novel Dual-Center Graph Clustering (DCGC) approach based on neighbor distribution properties, which includes representation learning with neighbor distribution and dual-center optimization. Specifically, we utilize neighbor distribution as a supervision signal to mine hard negative samples in contrastive learning, which is reliable and enhances the effectiveness of representation learning. Furthermore, neighbor distribution center is introduced alongside feature center to jointly construct a dual-target distribution for dual-center optimization. Extensive experiments and analysis demonstrate superior performance and effectiveness of our proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13765
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual-Center Graph Clustering with Neighbor Distribution
Cheng, Enhao
Zhang, Shoujia
Yin, Jianhua
Jin, Li
Nie, Liqiang
Machine Learning
Graph clustering is crucial for unraveling intricate data structures, yet it presents significant challenges due to its unsupervised nature. Recently, goal-directed clustering techniques have yielded impressive results, with contrastive learning methods leveraging pseudo-label garnering considerable attention. Nonetheless, pseudo-label as a supervision signal is unreliable and existing goal-directed approaches utilize only features to construct a single-target distribution for single-center optimization, which lead to incomplete and less dependable guidance. In our work, we propose a novel Dual-Center Graph Clustering (DCGC) approach based on neighbor distribution properties, which includes representation learning with neighbor distribution and dual-center optimization. Specifically, we utilize neighbor distribution as a supervision signal to mine hard negative samples in contrastive learning, which is reliable and enhances the effectiveness of representation learning. Furthermore, neighbor distribution center is introduced alongside feature center to jointly construct a dual-target distribution for dual-center optimization. Extensive experiments and analysis demonstrate superior performance and effectiveness of our proposed method.
title Dual-Center Graph Clustering with Neighbor Distribution
topic Machine Learning
url https://arxiv.org/abs/2507.13765