Saved in:
Bibliographic Details
Main Authors: Zhao, Peiyao, Li, Xin, Zhang, Zeyu, Wang, Mingzhong, Zhu, Xueying, Liao, Lejian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.05472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912224471154688
author Zhao, Peiyao
Li, Xin
Zhang, Zeyu
Wang, Mingzhong
Zhu, Xueying
Liao, Lejian
author_facet Zhao, Peiyao
Li, Xin
Zhang, Zeyu
Wang, Mingzhong
Zhu, Xueying
Liao, Lejian
contents Signed graph clustering is a critical technique for discovering community structures in graphs that exhibit both positive and negative relationships. We have identified two significant challenges in this domain: i) existing signed spectral methods are highly vulnerable to noise, which is prevalent in real-world scenarios; ii) the guiding principle ``an enemy of my enemy is my friend'', rooted in \textit{Social Balance Theory}, often narrows or disrupts cluster boundaries in mainstream signed graph neural networks. Addressing these challenges, we propose the \underline{D}eep \underline{S}igned \underline{G}raph \underline{C}lustering framework (DSGC), which leverages \textit{Weak Balance Theory} to enhance preprocessing and encoding for robust representation learning. First, DSGC introduces Violation Sign-Refine to denoise the signed network by correcting noisy edges with high-order neighbor information. Subsequently, Density-based Augmentation enhances semantic structures by adding positive edges within clusters and negative edges across clusters, following \textit{Weak Balance} principles. The framework then utilizes \textit{Weak Balance} principles to develop clustering-oriented signed neural networks to broaden cluster boundaries by emphasizing distinctions between negatively linked nodes. Finally, DSGC optimizes clustering assignments by minimizing a regularized clustering loss. Comprehensive experiments on synthetic and real-world datasets demonstrate DSGC consistently outperforms all baselines, establishing a new benchmark in signed graph clustering.
format Preprint
id arxiv_https___arxiv_org_abs_2502_05472
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Deep Signed Graph Clustering via Weak Balance Theory
Zhao, Peiyao
Li, Xin
Zhang, Zeyu
Wang, Mingzhong
Zhu, Xueying
Liao, Lejian
Social and Information Networks
Signed graph clustering is a critical technique for discovering community structures in graphs that exhibit both positive and negative relationships. We have identified two significant challenges in this domain: i) existing signed spectral methods are highly vulnerable to noise, which is prevalent in real-world scenarios; ii) the guiding principle ``an enemy of my enemy is my friend'', rooted in \textit{Social Balance Theory}, often narrows or disrupts cluster boundaries in mainstream signed graph neural networks. Addressing these challenges, we propose the \underline{D}eep \underline{S}igned \underline{G}raph \underline{C}lustering framework (DSGC), which leverages \textit{Weak Balance Theory} to enhance preprocessing and encoding for robust representation learning. First, DSGC introduces Violation Sign-Refine to denoise the signed network by correcting noisy edges with high-order neighbor information. Subsequently, Density-based Augmentation enhances semantic structures by adding positive edges within clusters and negative edges across clusters, following \textit{Weak Balance} principles. The framework then utilizes \textit{Weak Balance} principles to develop clustering-oriented signed neural networks to broaden cluster boundaries by emphasizing distinctions between negatively linked nodes. Finally, DSGC optimizes clustering assignments by minimizing a regularized clustering loss. Comprehensive experiments on synthetic and real-world datasets demonstrate DSGC consistently outperforms all baselines, establishing a new benchmark in signed graph clustering.
title Robust Deep Signed Graph Clustering via Weak Balance Theory
topic Social and Information Networks
url https://arxiv.org/abs/2502.05472