Research map / Probabilistic and scientific modeling / Molecules and proteins
Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
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 |
|---|---|---|---|
| Add graph-validity regularization to the VAE | VAE · QM9 | % Valid: 83.2 -> 96.6 | Helped |
| Add graph-validity regularization to the VAE | VAE · ZINC | % Valid: 29.6 -> 34.9 | Helped |
| Add graph-validity regularization to the VAE | VAE · Node-compatible | % Valid: 40.2 -> 98.4 | Helped |
| Add graph-validity regularization to the VAE | VAE · QM9 | ELBO: -17.3 -> -18.5 | Hurt |
| Add graph-validity regularization to the VAE | VAE · ZINC | ELBO: -46.5 -> -47.0 | Hurt |
| Add graph-validity regularization to the VAE | VAE · Node-compatible | ELBO: -42.5 -> -51.2 | Hurt |
| Add graph-validity regularization | VAE · Noisy node-compatible graphs | Percentage of validly decoded graphs: 11.2 -> 93.8 | Helped |
Closest papers by meaning
- Graph Generative Pre-trained Transformer (ICML 2025 · similarity 0.88)
- Bridging Molecular Graphs and Large Language Models (AAAI 2025 · similarity 0.86)
- Flatten Graphs as Sequences: Transformers are Scalable Graph Generators (NeurIPS 2025 · similarity 0.86)
- A Simple and Scalable Representation for Graph Generation (ICLR 2024 · similarity 0.86)
- Multi-View Empowered Structural Graph Wordification for Language Models (AAAI 2025 · similarity 0.86)
- GraphGPT: Generative Pre-trained Graph Eulerian Transformer (ICML 2025 · 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.