Abstract
Quantum machine learning is a promising direction for building more efficient and expressive models, particularly in domains where understanding complex, structured data is critical. We present the Quantum Graph Transformer (QGT), a hybrid graph-based architecture that integrates a quantum self-attention mechanism into the message-passing framework for structured language modeling. The attention mechanism is implemented using parameterized quantum circuits (PQCs), which enable the model to capture rich contextual relationships while significantly reducing the number of trainable parameters compared to classical attention mechanisms. We evaluate QGT on five sentiment classification benchmarks. Experimental results show that QGT consistently achieves higher or comparable accuracy than existing quantum natural language processing (QNLP) models, including both attention-based and non-attention-based approaches. When compared with an equivalent classical graph transformer, QGT yields an average accuracy improvement of 5.42% on real-world datasets and 4.76% on synthetic datasets. Additionally, QGT demonstrates improved sample efficiency, requiring nearly 50% fewer labeled samples to reach comparable performance on the Yelp dataset. These results highlight the potential of graph-based QNLP techniques for advancing efficient and scalable language understanding.
Abstract (translated)
量子机器学习是构建更高效和表达力更强的模型的一个有前景的方向，尤其是在理解复杂、结构化数据至关重要的领域。我们提出了一种基于图的混合架构——量子图变换器（Quantum Graph Transformer, QGT），它在结构化的语言建模中将量子自注意力机制整合到了消息传递框架内。该注意机制通过参数化量子电路（Parameterized Quantum Circuits，PQCs）实现，这使得模型能够捕捉丰富的上下文关系，并且相比传统的经典注意机制显著减少了可训练的参数数量。 我们在五个情感分类基准测试集上评估了QGT的效果。实验结果显示，QGT在准确度方面始终优于现有的量子自然语言处理（Quantum Natural Language Processing, QNLP）模型，包括基于注意力和非注意力的方法。与等效的经典图变换器相比，在真实世界数据集上，QGT的平均精度提高了5.42%，而在合成数据集上的提高为4.76%。此外，QGT还展示了更好的样本效率，仅需大约少一半数量的标记样本即可在Yelp数据集上达到类似性能。 这些结果突显了基于图的QNLP技术在推进高效和可扩展的语言理解方面的潜力。
URL
https://arxiv.org/abs/2506.07937
