PapersBenchmarks
Central China Research Institute for Artificial Intelligence Technologies
08 Nov 2024
computer-scienceartificial-intelligencemachine-learning

Improving Molecular Graph Generation with Flow Matching and Optimal Transport

Chinese Academy of Sciences logoChinese Academy of SciencesKing Abdullah University of Science and TechnologyInstitute of Computing TechnologyWestern Institute of Computing TechnologyCentral China Research Institute for Artificial Intelligence TechnologiesPhil Rivers Technology
Researchers from the Chinese Academy of Sciences and King Abdullah University of Science and Technology introduced GGFlow, the first discrete flow matching generative model that incorporates optimal transport for molecular graphs. This model achieves nearly perfect chemical validity and state-of-the-art performance in both unconditional and property-guided molecule generation with significantly fewer inference steps.
There are no more papers matching your filters at the moment.