Deep Graph Clustering Framework Based on Confidence-Guided Graph Enhancement and Dual-Negative Sample Contrastive Learning

Wang, Qiuming; Zhang, Sheng; Wu, Bing; Zhou, Jiangnan; Wu, Chennan; Zeng, Yirong; Sun, Ka; Liu, Chang

doi:10.3390/e28070763

Open AccessArticle

Deep Graph Clustering Framework Based on Confidence-Guided Graph Enhancement and Dual-Negative Sample Contrastive Learning

by

Qiuming Wang

,

Sheng Zhang

^*,

Bing Wu

,

Jiangnan Zhou

,

Chennan Wu

,

Yirong Zeng

,

Ka Sun

and

Chang Liu

School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China

^*

Author to whom correspondence should be addressed.

Entropy 2026, 28(7), 763; https://doi.org/10.3390/e28070763

Submission received: 30 May 2026 / Revised: 23 June 2026 / Accepted: 2 July 2026 / Published: 3 July 2026

(This article belongs to the Special Issue Advances in Complex Networks and Their Applications, from COMPLEX NETWORKS 2025)

Download

Browse Figures

Versions Notes

Abstract

Attributed graph clustering partitions nodes in an unsupervised manner by leveraging graph topology and node attributes. Existing deep methods face challenges including local structural bias, high noise in unsupervised graph editing, and insufficient discriminative ability for hard samples. To address these issues, we propose a deep graph clustering framework based on confidence-guided graph enhancement and dual-negative sample contrastive learning (CGEN). CGEN constructs a local–global dual-view representation learning module to fuse local neighborhood attributes with high-order global topological information. It then utilizes a confidence-guided conservative graph editing mechanism that integrates multiple constraints, specifically feature similarity, intra-cluster consistency, multi-view consistency, and pairwise node confidence, using a progressive update strategy for stable structural optimization. Furthermore, a dual-negative sample contrastive learning strategy dynamically adjusts the weights of attribute-confused and inter-cluster-confused negative samples to enhance discriminative ability near adjacent cluster boundaries. Extensive experiments on four benchmark datasets demonstrate that CGEN achieves highly competitive performance, outperforming the majority of state-of-the-art methods across core clustering metrics, thereby validating its effectiveness in addressing local structural bias, graph editing noise, and hard sample discriminative limitations.

Keywords: graph clustering; attributed graph; community structure; contrastive learning; data augmentation

Share and Cite

MDPI and ACS Style

Wang, Q.; Zhang, S.; Wu, B.; Zhou, J.; Wu, C.; Zeng, Y.; Sun, K.; Liu, C. Deep Graph Clustering Framework Based on Confidence-Guided Graph Enhancement and Dual-Negative Sample Contrastive Learning. Entropy 2026, 28, 763. https://doi.org/10.3390/e28070763

AMA Style

Wang Q, Zhang S, Wu B, Zhou J, Wu C, Zeng Y, Sun K, Liu C. Deep Graph Clustering Framework Based on Confidence-Guided Graph Enhancement and Dual-Negative Sample Contrastive Learning. Entropy. 2026; 28(7):763. https://doi.org/10.3390/e28070763

Chicago/Turabian Style

Wang, Qiuming, Sheng Zhang, Bing Wu, Jiangnan Zhou, Chennan Wu, Yirong Zeng, Ka Sun, and Chang Liu. 2026. "Deep Graph Clustering Framework Based on Confidence-Guided Graph Enhancement and Dual-Negative Sample Contrastive Learning" Entropy 28, no. 7: 763. https://doi.org/10.3390/e28070763

APA Style

Wang, Q., Zhang, S., Wu, B., Zhou, J., Wu, C., Zeng, Y., Sun, K., & Liu, C. (2026). Deep Graph Clustering Framework Based on Confidence-Guided Graph Enhancement and Dual-Negative Sample Contrastive Learning. Entropy, 28(7), 763. https://doi.org/10.3390/e28070763

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Deep Graph Clustering Framework Based on Confidence-Guided Graph Enhancement and Dual-Negative Sample Contrastive Learning

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI