Research map / Graph learning / Graph self-supervised learning
GGBall: Graph Generative Model on Poincaré Ball
Tianci Bu, Chuanrui Wang, Hao Ma, Haoren Zheng, Xin Lu, Tailin Wu
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 vector quantization (HVQVAE) to the hyperbolic autoencoder (ablation) | HAE · QM9 reconstruction | Validity: 95.18 -> 99.14 | Improved |
| add vector quantization (HVQVAE) to the hyperbolic autoencoder (ablation) | HAE · QM9 reconstruction | V.U.N.: 94.97 -> 97.34 | Improved |
| add vector quantization (HVQVAE) to the hyperbolic autoencoder (ablation) | HAE · Community-small reconstruction | Edge accuracy: 99.10 -> 99.39 | Improved |
| add vector quantization (HVQVAE) to the hyperbolic autoencoder (ablation) | HAE · Ego-small reconstruction | Edge accuracy: 92.40 -> 93.20 | Improved |
| add Riemannian flow matching prior to HVQVAE (ablation) | HVQVAE · Community-small generation | Avg. MMD: 0.0418 -> 0.0215 | Improved |
| add Riemannian flow matching prior to HVQVAE (ablation) | HVQVAE · Ego-small generation | Avg. MMD: 0.0154 -> 0.0112 | Improved |
| add Riemannian flow matching prior to HVQVAE (ablation) | HVQVAE · QM9 generation | V.U.N.: 64.44 -> 85.34 | Improved |
| use hyperbolic latent space instead of Euclidean (HVQVAE vs GraphVAE) | one-shot graph generator · Community-small generation | Avg. MMD: reducing the average MMD by 93.3% | Improved |
| use hyperbolic latent space instead of Euclidean (HVQVAE vs GraphVAE) | one-shot graph generator · Ego-small generation | Avg. MMD: reducing the average MMD by 86.8% | Improved |
| use Poincare ball instead of Lorentz model (ablation) | hyperbolic round-trip mapping · 64 dimensions round trip | L2 error: 2958.63 -> (8.86 ± 5.90)e-16 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GraphAF — GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation (ICLR 2020) · better on 3 of 3 shared results
- DiGress — DiGress: Discrete Denoising diffusion for graph generation (ICLR 2023) · better on 2 of 2 shared results
- GraphRNN — GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models (ICML 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Hyperbolic Geometric Latent Diffusion Model for Graph Generation (ICML 2024 · similarity 0.88)
- Residual Hyperbolic Graph Convolution Networks (AAAI 2024 · similarity 0.87)
- Hyperbolic Graph Diffusion Model (AAAI 2024 · similarity 0.87)
- Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation (NeurIPS 2026 · similarity 0.86)
- Geometric Generative Modeling with Noise-Conditioned Graph Networks (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.
