用于分子性质预测的量子和经典拓扑对齐架构的实现
Implementations of Quantum and Classical Topology-Aligned Architectures for Molecular Property Prediction
AI总结：
针对量子化学低数据和资源受限情况，提出拓扑对齐归纳偏差，用于分子性质预测。体现在变分量子电路Iso-QGNN和经典消息传递模型Iso-CGNN中，经QM9基准测试，参数高效，性能良好，表明该偏差是QM9规模驱动参数效率的关键，对量子机器学习基准测试有影响。
AI中文摘要：
在量子化学典型的低数据和资源受限情况下，参数高效学习是关键目标。本文提出一种拓扑对齐归纳偏差，模型架构反映分子键图，原子映射到固定计算单元寄存器，键决定通过共享可学习参数相互作用的对。该原理体现在两种架构中：变分量子电路（Iso-QGNN）和参数匹配经典消息传递模型（Iso-CGNN）。在QM9基准上对模型进行HOMO-LUMO和偶极矩二元分类任务测试。64个可训练参数的实现，在间隙任务上量子模型测试AUC约为0.88，经典模型约为0.91，偶极矩任务两者接近0.78。模型在约250个训练分子内达到90%渐近性能，训练中梯度范数保持稳定。这些结果表明拓扑对齐归纳偏差是QM9规模驱动参数效率的关键因素，对量子机器学习中的匹配基线基准测试有影响。
英文摘要：
For low-data and resource-constrained regimes typical of quantum chemistry, parameter-efficient learning is a key objective. Here, we propose a topology-aligned inductive bias in which the model architecture mirrors the molecular bond graph: atoms map to a fixed register of computational units, and bonds determine which pairs interact through shared learnable parameters. This principle is instantiated in two architectures: a variational quantum circuit (Iso-QGNN) and a parameter-matched classical message-passing network (Iso-CGNN). The models are benchmarked on HOMO-LUMO and dipole moment binary classification tasks over the QM9 benchmark. With 64 trainable parameters, the implementations achieve test AUCs of approximately 0.89 (quantum) and 0.92 (classical) on the gap task, and close to 0.78 (both) on the dipole task. The models reach 90% of asymptotic performance within about 300 training molecules and gradient norms remain stable throughout training. These results indicate that the topology-aligned inductive bias is the active ingredient driving parameter efficiency at QM9 scale, with implications for matched-baseline benchmarking in quantum machine learning.
