Research map / Graph learning / GNN architectures
Mean-field theory of graph neural networks in graph partitioning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use a deep GNN instead of a shallower network (ablation) | GNN trained by backpropagation · Symmetric SBM, c=8 | overlap | Helped |
| Train model parameters by backpropagation | GNN · Symmetric SBM | overlap | Helped |
| Train model parameters by backpropagation | GNN · Symmetric SBM, large-graph limit | detectability threshold | No clear effect |
| Use φ(Xᵀ) rather than Xᵀ for k-means readout (ablation) | Untrained GNN · Symmetric SBM | overlap | Helped |
| Use φ(Xᵀ) rather than Xᵀ for k-means readout (ablation) | Trained GNN · Symmetric SBM | overlap | No clear effect |
| Use ResNet skip connections and batch normalization (ablation) | Deep GNN · Symmetric SBM | parameter learning | Helped |
Closest papers by meaning
- Do Graph Neural Networks Learn Generalizable Algorithms for Clustering Graphs? (NeurIPS 2026 · similarity 0.89)
- Neural Trees for Learning on Graphs (NeurIPS 2021 · similarity 0.89)
- Generalization Error of Graph Neural Networks in the Mean-field Regime (ICML 2024 · similarity 0.89)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.88)
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.88)
- Almost Surely Asymptotically Constant Graph Neural Networks (NeurIPS 2024 · similarity 0.88)
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.