MolPaQ: Modular Quantum-Classical Patch Learning for Interpretable Molecular Generation
For molecular generation, MolPaQ offers a modular quantum-classical approach that improves property control without sacrificing validity or diversity, though gains are incremental.
MolPaQ achieves 100% RDKit validity, 99.75% novelty, and 0.905 diversity on QM9, while improving mean QED by ~2.3% and aromatic motif incidence by ~10-12% over a classical baseline.
Molecular generative models must jointly ensure validity, diversity, and property control, yet existing approaches typically trade off among these objectives. We present MOLPAQ, a modular quantum-classical generator that assembles molecules from quantum-generated latent patches. A \b{eta}-VAE pretrained on QM9 learns a chemically aligned latent manifold; a reduced conditioner maps molecular descriptors into this space; and a parameter-efficient quantum patch generator produces entangled node embeddings that a valence-aware aggregator reconstructs into valid molecular graphs. Adversarial fine-tuning with a latent critic and chemistry-shaped reward yields 100\% RDKit validity, 99.75\% novelty, and 0.905 diversity. Beyond aggregate metrics, the pretrained quantum generator, steered by the conditioner, improves mean QED by approx. 2.3\% and increases aromatic motif incidence by approx. 10-12\% relative to a parameter-matched classical generator, highlighting its role as a compact topology-shaping operator.