Research map / Graph learning / Graph self-supervised learning
Constrained Graph Variational Autoencoders for Molecule Design
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 |
|---|---|---|---|
| Remove the distance feature from edge-selection features (ablation) | CGVAE · ZINC | ring-count statistics | Hurt |
| Assume independent edge generation and sample the molecule in one step (ablation) | CGVAE · Molecule generation | ring-count statistics | Hurt |
| Remove GGNN decoder updates while retaining sequential construction (ablation) | CGVAE · Molecule generation | ring-count statistics | Hurt |
| Train using 50 generation traces per molecule instead of a single trace (ablation) | CGVAE · ZINC | ring-statistic matching | Helped |
| Perform gradient ascent in the latent space using the trained QED-scoring network | CGVAE · ZINC molecule optimization | real QED: 0.4419 -> 0.8796 | Helped |
Closest papers by meaning
- Junction Tree Variational Autoencoder for Molecular Graph Generation (ICML 2018 · similarity 0.94)
- NeVAE: A Deep Generative Model for Molecular Graphs (AAAI 2019 · similarity 0.92)
- 3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design (ICML 2022 · similarity 0.90)
- Graph Generative Pre-trained Transformer (ICML 2025 · similarity 0.88)
- Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space (ICLR 2025 · similarity 0.87)
- The quest for the GRAph Level autoEncoder (GRALE) (NeurIPS 2025 · similarity 0.87)
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.