量子注意力机制提升图学习，让量子模型更好预测分子性质。
Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning
- 用可训练量子电路+量子注意力编码节点与邻域信息
- 大分子图上性能显著优于无注意力的量子模型
- 小分子图表现接近经典图注意力模型，适合化学等领域
我们提出量子图注意力网络（QGAT），作为图结构上归纳学习的可训练量子编码器，扩展了量子图神经网络（QGNN）框架。QGAT利用参数化量子电路编码节点特征与邻域结构，并通过动态学习的酉变换实现量子注意力机制，调节各邻居贡献。该方法生成具有表达力且关注局部结构的量子表示，能泛化至未见图实例。我们在QM9数据集上评估，目标为预测多种化学性质。实验对比了带与不带注意力的经典与量子图神经网络，结果表明注意力在两类模型中均持续提升性能。值得注意的是，随着图规模增大，量子注意力优势愈发明显，QGAT在大分子图上显著优于非注意力量子模型；而在小分子图上，其预测精度可媲美经典GAT模型，证明其作为高表达力量子编码器的可行性。这些结果展示了量子注意力机制在增强QGNN归纳能力方面的潜力，适用于化学等场景。
原文摘要 · Abstract (English)
We introduce Quantum Graph Attention Networks (QGATs) as trainable quantum encoders for inductive learning on graphs, extending the Quantum Graph Neural Networks (QGNN) framework. QGATs leverage parameterized quantum circuits to encode node features and neighborhood structures, with quantum attention mechanisms modulating the contribution of each neighbor via dynamically learned unitaries. This allows for expressive, locality-aware quantum representations that can generalize across unseen graph instances. We evaluate our approach on the QM9 dataset, targeting the prediction of various chemical properties. Our experiments compare classical and quantum graph neural networks-with and without attention layers-demonstrating that attention consistently improves performance in both paradigms. Notably, we observe that quantum attention yields increasing benefits as graph size grows, with QGATs significantly outperforming their non-attentive quantum counterparts on larger molecular graphs. Furthermore, for smaller graphs, QGATs achieve predictive accuracy comparable to classical GAT models, highlighting their viability as expressive quantum encoders. These results show the potential of quantum attention mechanisms to enhance the inductive capacity of QGNN in chemistry and beyond.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。