Research map / Graph learning / Graph algorithms and clustering
DGCBench: A Deep Graph Clustering Benchmark
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Presents DGCBench, a benchmark for deep graph clustering addressing the lack of unified datasets, evaluation protocols, and metrics.
Problem
Deep graph clustering lacks ground-truth labels for model design and standardized benchmarks, with no unified datasets, evaluation protocols, or metrics.
Approach
A unified benchmark for deep graph clustering providing common datasets, evaluation protocols, and metrics to enable standardized comparison of DGC methods.
Closest papers by meaning
- DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (AAAI 2024 · similarity 0.92)
- Dink-Net: Neural Clustering on Large Graphs (ICML 2023 · similarity 0.90)
- Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation (ICML 2025 · similarity 0.90)
- Deep Temporal Graph Clustering (ICLR 2024 · similarity 0.88)
- Local Graph Clustering with Noisy Labels (ICLR 2024 · similarity 0.87)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.