Research map / Graph learning / Graph self-supervised learning
Stochastic Blockmodels meet Graph Neural Networks
Nikhil Mehta, Lawrence Carin Duke, Piyush Rai
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add nonlinear encoder and decoder to the LFRM-style model | DGLFRM-B vs LFRM · NIPS12 | AUC ROC: 0.8489 \pm .0001 -> 0.8898\pm.0028 | Improved |
| add nonlinear encoder and decoder to the LFRM-style model | DGLFRM-B vs LFRM · Cora | AUC ROC: 0.9096\pm.0026 -> 0.9281\pm.0024 | Improved |
| use sparse real-valued membership strengths instead of binary-only embeddings (ablation) | DGLFRM · Citeseer | AUC ROC: 0.9007\pm.0020 -> 0.9379\pm.0032 | Improved |
| use sparse real-valued membership strengths instead of binary-only embeddings (ablation) | DGLFRM · Cora | Average Precision: 0.9259\pm.0023 -> 0.9376\pm.0022 | Improved |
| use binary embeddings instead of sparse real-valued embeddings (ablation) | DGLFRM · NIPS12 | AUC ROC: 0.8734\pm.0043 -> 0.8898\pm.0028 | Improved |
| use binary embeddings instead of sparse real-valued embeddings (ablation) | DGLFRM · Yeast | AUC ROC: 0.7856\pm.0005 -> 0.8061\pm.0003 | Improved |
| use binary embeddings instead of sparse real-valued embeddings (ablation) | DGLFRM · Pubmed | AUC ROC: 0.9395\pm.0008 -> 0.9396\pm.0052 | No clear effect |
| include node features rather than ignoring them (ablation) | DGLFRM · Cora, Citeseer, and Pubmed | AUC ROC | Improved |
| use structured mean-field instead of vanilla mean-field inference (ablation) | DGLFRM · link prediction experiments | link prediction performance | Improved |
Closest papers by meaning
- From Your Block to Our Block: How to Find Shared Structure Between Stochastic Block Models over Multiple Graphs (AAAI 2025 · similarity 0.88)
- SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion (ICML 2025 · similarity 0.87)
- Multi-View Stochastic Block Models (ICML 2024 · similarity 0.87)
- Convergence Guarantees for the DeepWalk Embedding on Block Models (ICML 2024 · similarity 0.86)
- Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models (ICML 2025 · similarity 0.85)
- Analysis of Corrected Graph Convolutions (NeurIPS 2024 · similarity 0.85)
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.
