Variational Quantum Attention for Molecular Graph Learning
Abstract
Molecular property prediction is central to computational drug discovery, where graph neural networks learn to weight neighboring atomic environments during message passing. Yet it remains unclear how variational quantum circuits alter learned attention behavior in molecular graphs. We introduce an edge-aware variational quantum attention mechanism for molecular graph learning, in which the receiving atom, neighboring atom, and connecting bond jointly determine the quantum attention state. Across five molecular property and bioactivity prediction tasks, QGAT achieves competitive performance relative to GATv2, with a consistent improvement on BBBP across all six evaluated circuit ansatzes. We further compare how the quantum and classical attention scores weight molecular structure beyond accuracy. In the Verubecestat BACE1 inhibitor series, QGAT achieves a higher Spearman correlation than GATv2 and assigns positive attributions to several structural changes consistent with reported structure-activity relationships (SARs). This case study shows that the two attention mechanisms can exhibit different prediction and attribution behavior across structurally related BACE1 analogues, while broader validation is required to determine how consistently these differences generalize across chemical series and targets. Circuit ablations further show that performance depends on the circuit design. Together, these results show that variational quantum attention can serve as a viable alternative molecular attention parameterization while inducing circuit- and chemistry-dependent behavior distinct from a matched classical scorer.
Related
- Finite-element-assisted interpretable graph attention learning for high-fidelity prediction of mass transport in fibrin biomaterials
- Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits
- Hierarchical Fourier Approximation for Variational Quantum Distribution Learning
- Hybrid quantum-classical attention for histopathology-based molecular profiling in data-limited cancers
- Operator Learning with Variational Quantum Circuits
BibTeX
@misc{lin2026variational,
title = {{Variational Quantum Attention for Molecular Graph Learning}},
author = {Yu-Cheng Lin and Yu-Chao Hsu and Tai-Yue Li and Nan-Yow Chen and Samuel Yen-Chi Chen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.04588},
eprint = {2610.04588},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.04588},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Variational Quantum Attention for Molecular Graph Learning
AU - Yu-Cheng Lin
AU - Yu-Chao Hsu
AU - Tai-Yue Li
AU - Nan-Yow Chen
AU - Samuel Yen-Chi Chen
PY - 2026
DA - 2026/10/03
PB - arXiv
DO - 10.48550/arxiv.2610.04588
UR - https://arxiv.org/abs/2610.04588
AB - Molecular property prediction is central to computational drug discovery, where graph neural networks learn to weight neighboring atomic environments during message passing. Yet it remains unclear how variational quantum circuits alter learned attention behavior in molecular graphs. We introduce an edge-aware variational quantum attention mechanism for molecular graph learning, in which the receiving atom, neighboring atom, and connecting bond jointly determine the quantum attention state. Across five molecular property and bioactivity prediction tasks, QGAT achieves competitive performance relative to GATv2, with a consistent improvement on BBBP across all six evaluated circuit ansatzes. We further compare how the quantum and classical attention scores weight molecular structure beyond accuracy. In the Verubecestat BACE1 inhibitor series, QGAT achieves a higher Spearman correlation than GATv2 and assigns positive attributions to several structural changes consistent with reported structure-activity relationships (SARs). This case study shows that the two attention mechanisms can exhibit different prediction and attribution behavior across structurally related BACE1 analogues, while broader validation is required to determine how consistently these differences generalize across chemical series and targets. Circuit ablations further show that performance depends on the circuit design. Together, these results show that variational quantum attention can serve as a viable alternative molecular attention parameterization while inducing circuit- and chemistry-dependent behavior distinct from a matched classical scorer.
ER -