Research map / Graph learning / Graph self-supervised learning
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
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 dependent edge-level RNN rather than independent Bernoulli edge predictions (ablation) | GraphRNN · Grid | Orbit MMD: 0.011 -> $\mathbf{10^{-4}}$ | Helped |
| Use a dependent edge-level RNN rather than independent Bernoulli edge predictions (ablation) | GraphRNN · Protein | Orbit MMD: 0.037 -> 0.217 | Hurt |
| Use a dependent edge-level RNN rather than independent Bernoulli edge predictions (ablation) | GraphRNN · Community-small | Clustering MMD: 0.15 -> 0.03 | Helped |
| Use a dependent edge-level RNN rather than independent Bernoulli edge predictions (ablation) | GraphRNN · Ego-small | Degree MMD: 0.002 -> 0.0003 | Helped |
| Use a dependent edge-level RNN rather than independent Bernoulli edge predictions (ablation) | GraphRNN · Ego-small | Test NLL: 9.88 -> 10.61 | Hurt |
| Use GraphRNN instead of traditional graph-generation baselines | GraphRNN · Community, Ego, Grid, Protein | MMD | Mixed |
| Use GraphRNN instead of deep graph-generation baselines | GraphRNN · Community-small, Ego-small | MMD | Helped |
| Train GraphRNN on graphs between the B-A and E-R structures | GraphRNN · B-A/E-R interpolation | Degree and clustering MMD | Helped |
Closest papers by meaning
- Geometric Generative Modeling with Noise-Conditioned Graph Networks (ICML 2025 · similarity 0.89)
- Efficient and Scalable Graph Generation through Iterative Local Expansion (ICLR 2024 · similarity 0.88)
- HiGen: Hierarchical Graph Generative Networks (ICLR 2024 · similarity 0.88)
- Towards Addressing Frontiers in Graph Generation (AAAI 2025 · similarity 0.88)
- On the Role of Edge Dependency in Graph Generative Models (ICML 2024 · similarity 0.88)
- SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion (ICML 2025 · 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.