Quantum-Inspired Structure-Aware Diffusion for Efficient 3D Molecular Generation

Zisen Shan, Lianghong Chen, Pingzhao Hu

Keywords: Quantum Machine Learning, Quantum Diffusion Model, 3D Molecular Generation

TL;DR: We propose the first fully quantum diffusion model (SQ-Diff) for efficient 3D molecule generation, leveraging a quantum U-Net architecture and novel structural encoding.

Abstract: The high computational cost of classical diffusion models can limit their use in large-scale 3D molecular generation for drug and material discovery. We introduce $\textbf{S}$tructure-aware $\textbf{Q}$uantum $\textbf{Diff}$usion (SQ-Diff), the first full quantum diffusion model for this task, designed to leverage potential quantum advantages in the Noisy Intermediate-Scale Quantum era. Structural priors (e.g., inter-atomic distances) are encoded into the initial quantum state via a novel state preparation procedure that yields a unified normalization scheme dependent only on the number of atoms. The denoising process is driven by a Quantum U-Net, a fully quantum architecture that combines learnable variational quantum circuits with parameter-free operators. Training is guided by these structural priors enforced through a graph-based objective function to maintain structural consistency. Experimentally, SQ-Diff generates valid and diverse 3D molecules and shows improved performance over existing quantum-based methods. While a gap in generation quality compared to leading classical models remains, our model matches the inference speed of the fastest classical approaches with only a few quantum parameters, setting a new benchmark for pure quantum generative models.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 11805