Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning
This work addresses the challenge of enhancing quantum graph neural networks for chemistry applications, representing an incremental advancement in quantum machine learning.
The authors tackled the problem of inductive graph learning by introducing Quantum Graph Attention Networks (QGATs) as trainable quantum encoders, achieving significant performance improvements over non-attentive quantum models on larger molecular graphs and comparable accuracy to classical models on smaller ones.
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.