Skip to content

DGCBench: A Deep Graph Clustering Benchmark

2025 · Neural Information Processing Systems · pp. 19328-19353 · 5 citations · 72 references
Computer Science

TL;DR

This work introduces DGCBench, the first comprehensive and unified benchmark for DGC methods, and develops PyDGC, an open-source Python library that standardizes the DGC training and evaluation paradigm.

Abstract

Deep graph clustering (DGC) aims to partition graph nodes into distinct clusters in an unsupervised manner. Despite rapid advancements in this field, DGC remains inherently challenging due to the absence of ground-truth, which complicates the design of effective algorithms and impedes the establishment of standardized benchmarks. The lack of unified datasets, evaluation protocols, and metrics further exacerbates these challenges, making it difficult to systematically assess and compare DGC methods. To address these limitations, we introduce DGCBench , the first comprehensive and unified benchmark for DGC methods. It evaluates 12 state-of-the-art DGC methods across 12 datasets from diverse domains and scales, spanning 6 critical dimensions: discriminability , effectiveness , scalability , efficiency , stability , and robustness . Additionally, we develop PyDGC , an open-source Python library that standardizes the DGC training and evaluation paradigm. Through systematic experiments, we reveal persistent limitations in existing methods, specifically regarding the homophily bottleneck, training instability, vulnerability to perturbations, efficiency plateau, scalability challenges, and poor discriminability, thereby offering actionable insights for future research. We hope that DGCBench , PyDGC , and our analyses will collectively accelerate the progress in the DGC community. The code is available at https:/

View source

Similar papers

#machine learning Open access May 2024

Robustness of shallow graph embedding methods for community detection

The robustness of shallow graph embedding methods for community detection in the face of network perturbations is found to be influenced by factors such as network size, initial community partition strength, and the type of perturbation.

Zhi-Feng Wei, P. Moriano, Ramakrishnan Kannan · 3 citations
Review Sep 2026

A Comprehensive Study of Graph Neural Networks: Types and Application

This systematic review presents a comprehensive analysis of graph neural networks (GNNs), focusing on their major types and applications. GNNs have emerged as an effective deep learning (DL) method for modelling and analysing intricate relationships in graph‐structured data. Their versatility has led to widespread ad...

Rahul Dubey, Ramandeep Kaur, Nidhi Ahuja · 4 citations
#machine learning Preprint Sep 2026

SynCo: Synthetic Community-Aware Attributed Graph Generator for Graph Neural Network Benchmarking

This work introduces the Synthetic Community-Aware Attributed Graph Generator (SynCo), a graph generation algorithm that allows users to control the node degree distribution and sub-community structure and outperforms state-of-the-art approaches in synthetic graph generation and data augmentation.

Guilherme Henrique Messias, M. C. de Souza, Sylvia Iasulaitis et al. · 0 citations

Scalable and Expressive Graph Representation Learning with Temporal, Structural, and Zero-Shot Capabilities

Graph representation learning has emerged as a foundational discipline within modern data science, essential for modeling the complex relational systems ubiquitous in domains from social networks to bioinformatics. However, conventional approaches, particularly Graph Neural Networks (GNN), exhibit significant limitatio...

Justin Carpenter · 0 citations

E ! icient Partition-based Approaches for Diversified Top-𝐿 Subgraph Matching

The Partition-based Distance Diversity (PDD) framework is introduced, which partitions the graph and retrieves diverse matches from distant regions and two optimizations are developed: embedding-driven partition ! ltering and densest-based partition selection over a Partition Adjacency Graph.

Liu-Yi Chen, Yucheng Hu, Zheng-Yi Yang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.