Generative Learning


Generative learning in chemistry allows the prediction of new molecules based on the models build e.g. for properties of a known set of molecules. This allows for example the automated design of new catalysts with improved properties. Approaches to generative learning explored in C-CAS include genetic algorithms in CoDECs and the use of large language models (LLMs).


  • Guo, Z., Yu, W., Zhang, C., Jiang, M. and Chawla, N.V. GraSeq: Graph and Sequence Fusion Learning for Molecular Property Prediction. Proc. 29th ACM Intl. Conf. Inf. Knowl. Manag. 2020, 435-443.

  • Guo, Taicheng, Kehan Guo, Zhengwen Liang, Zhichun Guo, Nitesh V. Chawla, Olaf Wiest, and Xiangliang Zhang. "What can GPT models do in chemistry? A comprehensive benchmark on eight tasks." NeurIPS 2023, accepted.