Transfer learning of GW-Bethe-Salpeter Equation excitation energies

TL;DR

This paper demonstrates that transfer learning with graph neural networks pretrained on low-fidelity data can accurately predict high-fidelity quasiparticle and excitation energies, reducing data requirements and improving generalization in electronic-structure calculations.

Contribution

The study introduces a transfer learning approach that leverages low-fidelity DFT and TDDFT data to enhance high-fidelity qsGW and qsGW-BSE predictions, enabling accurate results with limited high-quality data.

Findings

Pretraining improves prediction accuracy.

Reduces dependence on costly high-fidelity data.

Mitigates large outliers for diverse molecules.

Abstract

A persistent challenge in machine learning for electronic-structure calculations is the sharp imbalance between abundant low-fidelity data like DFT or TDDFT results and the scarcity of high-fidelity data like many-body perturbation theory labels. We show that transfer learning provides an effective route to bridge this gap: graph neural networks pretrained on DFT and TDDFT properties can be finetuned with limited qs$GW$ and qs$GW$-BSE data to yield accurate predictions of quasiparticle and excitation energies. Assessing both full-model and readout-only finetuning across chemically diverse test sets, we find that pretraining improves accuracy, reduces reliance on costly qs$GW$ data, and mitigates large predictive outliers even for molecules larger or chemically distinct from those seen during finetuning. Our results demonstrate that multi-fidelity transfer learning can substantially extend the reach of many-body-level predictions across chemical space.