Research map / Graph learning / Graph self-supervised learning
Learning Hyperedge Replacement Grammars for Graph Generation
Salvador Aguiñaga, David Chiang, Tim Weninger
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 |
|---|---|---|---|
| use HRG instead of Chung-Lu | graph generator · Enron | GCD: 1.33 -> 0.51 | Improved |
| use HRG instead of Kronecker | graph generator · Routers | GCD: 2.81 -> 1.41 | Improved |
| use HRG instead of Chung-Lu | graph generator · DBLP | GCD: 1.73 -> 1.59 | Improved |
| use HRG instead of Chung-Lu | graph generator · arXiv | GCD: 1.82 -> 1.10 | Improved |
| extrapolate graphs up to 32x from small graphs with HRG | HRG · Karate Club and Protein extrapolation | GCD | Improved |
| apply model repeatedly ten times (infinity mirror) | HRG vs Kronecker and Chung-Lu · Routers, arXiv, Enron, DBLP | GCD | Improved |
| increase number of sampled subgraphs k (ablation) | HRG · Routers | model size: r = 0.31, p = 0.07 | Mixed |
| increase sampled subgraph size s (ablation) | HRG · Routers | model size: r = 0.64 | Improved |
| increase HRG model size (more rules) (ablation) | HRG · Routers | GCD: r = -0.12, p = 0.49 | No clear effect |
| increase HRG model size (more rules) (ablation) | HRG · DBLP | GCD: r = -0.08, p = 0.62 | No clear effect |
| increase HRG model size (ablation) | HRG · Routers | extraction time: r = 0.68 | Hurt |
Closest papers by meaning
- How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension (ICLR 2025 · similarity 0.87)
- Generative Graph Pattern Machine (NeurIPS 2025 · similarity 0.87)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.87)
- Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport (AAAI 2025 · similarity 0.87)
- Beyond Message Passing: Neural Graph Pattern Machine (ICML 2025 · similarity 0.86)
- Towards Addressing Frontiers in Graph Generation (AAAI 2025 · similarity 0.86)
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.
