Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Xunlian, Hu, Jingqi, Zhang, Anqi, Quan, Yining, Miao, Qiguang, Sun, Peng Gang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.09790
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911993900826624
author Wu, Xunlian
Hu, Jingqi
Zhang, Anqi
Quan, Yining
Miao, Qiguang
Sun, Peng Gang
author_facet Wu, Xunlian
Hu, Jingqi
Zhang, Anqi
Quan, Yining
Miao, Qiguang
Sun, Peng Gang
contents Graph clustering is a crucial task in network analysis with widespread applications, focusing on partitioning nodes into distinct groups with stronger intra-group connections than inter-group ones. Recently, contrastive learning has achieved significant progress in graph clustering. However, most methods suffer from the following issues: 1) an over-reliance on meticulously designed data augmentation strategies, which can undermine the potential of contrastive learning. 2) overlooking cluster-oriented structural information, particularly the higher-order cluster(community) structure information, which could unveil the mesoscopic cluster structure information of the network. In this study, Structure-enhanced Contrastive Learning (SECL) is introduced to addresses these issues by leveraging inherent network structures. SECL utilizes a cross-view contrastive learning mechanism to enhance node embeddings without elaborate data augmentations, a structural contrastive learning module for ensuring structural consistency, and a modularity maximization strategy for harnessing clustering-oriented information. This comprehensive approach results in robust node representations that greatly enhance clustering performance. Extensive experiments on six datasets confirm SECL's superiority over current state-of-the-art methods, indicating a substantial improvement in the domain of graph clustering.
format Preprint
id arxiv_https___arxiv_org_abs_2408_09790
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Structure-enhanced Contrastive Learning for Graph Clustering
Wu, Xunlian
Hu, Jingqi
Zhang, Anqi
Quan, Yining
Miao, Qiguang
Sun, Peng Gang
Machine Learning
Graph clustering is a crucial task in network analysis with widespread applications, focusing on partitioning nodes into distinct groups with stronger intra-group connections than inter-group ones. Recently, contrastive learning has achieved significant progress in graph clustering. However, most methods suffer from the following issues: 1) an over-reliance on meticulously designed data augmentation strategies, which can undermine the potential of contrastive learning. 2) overlooking cluster-oriented structural information, particularly the higher-order cluster(community) structure information, which could unveil the mesoscopic cluster structure information of the network. In this study, Structure-enhanced Contrastive Learning (SECL) is introduced to addresses these issues by leveraging inherent network structures. SECL utilizes a cross-view contrastive learning mechanism to enhance node embeddings without elaborate data augmentations, a structural contrastive learning module for ensuring structural consistency, and a modularity maximization strategy for harnessing clustering-oriented information. This comprehensive approach results in robust node representations that greatly enhance clustering performance. Extensive experiments on six datasets confirm SECL's superiority over current state-of-the-art methods, indicating a substantial improvement in the domain of graph clustering.
title Structure-enhanced Contrastive Learning for Graph Clustering
topic Machine Learning
url https://arxiv.org/abs/2408.09790