Embedded Graph Flows learns continuous embeddings for graph categories and uses flow matching with a permutation-equivariant transformer to generate molecular graphs, achieving state-of-the-art results on QM9.
Fréchet chemnet distance: A metric for generative models for molecules in drug discovery
6 Pith papers cite this work, alongside 343 external citations. Polarity classification is still indexing.
6
Pith papers citing it
343
external citations · Crossref
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
Transport Novelty Distance (TNovD) couples training and generated crystal embeddings via optimal transport and penalizes both memorized and unrealistic samples with a two-regime cost.
GraphBSI uses Bayesian Sample Inference as noise-controlled SDEs to generate discrete graphs in one shot, achieving state-of-the-art results on molecular benchmarks Moses and GuacaMol.
A grammar-based graph generator with domain-specific coarsening produces feasible molecular and RNA graphs with long-range constraints.
Pretraining LLMs on deterministic SMILES parsing tasks improves molecular structural understanding and downstream chemistry performance.
citing papers explorer
-
Embedded Graph Flows for Categorical Graph Generation
Embedded Graph Flows learns continuous embeddings for graph categories and uses flow matching with a permutation-equivariant transformer to generate molecular graphs, achieving state-of-the-art results on QM9.
- Multimarginal flow matching with optimal transport potentials