Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers

Despite the remarkable progress of machine learning (ML) techniques in chemistry, modeling the optoelectronic properties of long conjugated oligomers and polymers with ML remains challenging due to the difficulty in obtaining sufficient training data. Here, we use transfer learning to address the data scarcity issue by pre-training graph neural networks using data from short oligomers. With only a few hundred training data, we are able to achieve an average error of about 0.1 eV for the excited-state energy of oligothiophenes against time-dependent density functional theory (TDDFT) calculations. We show that the success of our transfer learning approach relies on the relative locality of low-lying electronic excitations in long conjugated oligomers. Finally, we demonstrate the transferability of our approach by modeling the lowest-lying excited-state energies of poly(3-hexylthiophene) in its single-crystal and solution phases using the transfer learning models trained with the data of gas-phase oligothiophenes. The transfer learning predicted excited-state energy distributions agree quantitatively with TDDFT calculations and capture some important qualitative features observed in experimental absorption spectra.

Automated summary

This study addresses the challenge of modeling the optoelectronic properties of long conjugated oligomers and polymers in chemistry using transfer learning, achieving accurate modeling of excited-state energy of oligothiophenes. The success of the transfer learning approach relies on the relative locality of low-lying electronic excitations in long conjugated oligomers, demonstrating its transferability in modeling poly(3-hexylthiophene) excited-state energies. The predicted energy distributions agree quantitatively with TDDFT calculations and capture important qualitative features observed in experimental absorption spectra.