Improving Molecular Graph Generation with Flow Matching and Optimal Transport
This work improves molecular graph generation for drug discovery, representing an incremental advancement over diffusion models with specific gains in training stability and sampling efficiency.
The paper tackles the challenge of generating molecular graphs for drug design by proposing GGFlow, a discrete flow matching model with optimal transport that addresses unstable training and inefficient sampling in diffusion models. The method demonstrates superior performance on unconditional and conditional molecule generation tasks, outperforming existing baselines.
Generating molecular graphs is crucial in drug design and discovery but remains challenging due to the complex interdependencies between nodes and edges. While diffusion models have demonstrated their potentiality in molecular graph design, they often suffer from unstable training and inefficient sampling. To enhance generation performance and training stability, we propose GGFlow, a discrete flow matching generative model incorporating optimal transport for molecular graphs and it incorporates an edge-augmented graph transformer to enable the direct communications among chemical bounds. Additionally, GGFlow introduces a novel goal-guided generation framework to control the generative trajectory of our model, aiming to design novel molecular structures with the desired properties. GGFlow demonstrates superior performance on both unconditional and conditional molecule generation tasks, outperforming existing baselines and underscoring its effectiveness and potential for wider application.