We propose Quantum Graph Transformers (QGT), a novel approach for realizing the Transformer architecture for graph learning with quantum processors. QGT is built on top of the Graph Trans-former (GT) architecture and addresses the main challenge of mapping GT basic functions such as node encodings, graph structure, all-to-all connectivity, and message passing to quantum computing primitives and processors. We empirically demonstrate the training and inference efficacy of our proposed QGT architecture for the graph classification task on quantum devices over various graph datasets.
We propose Quantum Graph Transformers (QGT), a novel approach for realizing the Transformer architecture for graph learning with quantum processors. QGT is built on top of the Graph Trans-former (GT) architecture and addresses the main challenge of mapping GT basic functions such as node encodings, graph structure, all-to-all connectivity, and message passing to quantum computing primitives and processors. We empirically demonstrate the training and inference efficacy of our proposed QGT architecture for the graph classification task on quantum devices over various graph datasets.
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 demonstrate that QGT effectively learns sentiment representations, achieving accuracies of 93.0%, 90.5%, and 88.0% on the Yelp, IMDB, and Amazon datasets, and 100% and 95.12% on the synthetic MC and RP datasets, respectively. These results highlight the potential of graph-based quantum NLP techniques for advancing efficient and scalable language understanding.
ABSTRACT Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT) , a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self‐attention. The QGT models variable‐length sentences as token graphs, where both the embedding encoding and the self‐attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and ‐nearest‐neighbor graph structures and evaluate it on five benchmark sentiment‐classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving fewer parameters while requiring 3– fewer samples to reach comparable performance. These findings highlight the potential of graph‐based quantum models as scalable and data‐efficient architectures for natural language understanding.
Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data, but training and inference on large graphs are often bottlenecked by memory constraints and sparse linear-algebra workloads. Quantum computing offers an alternative set of primitives that may improve scalability for graph learning. Building on the quantum graph neural network (QGNN) framework of Liao \textit{et al.}, this work implements two representative architectures --- the Simplified Graph Convolution (SGC) and Linear Graph Convolution (LGC) models --- and evaluates them on open benchmark graph datasets and semi-supervised learning tasks using quantum simulation. We compare predictive performance and optimization behavior against classical baselines, showing that the quantum models achieve competitive performance with fewer parameters. Finally, we present a cost gradient analysis that identifies the tasks for which the models showcased are trainable. This is followed by a classical simulability study to find regimes in which the proposed circuits remain robust during training.
Sentiment classification remains challenging due to subtle semantic cues and long-range contextual dependencies that are often difficult for existing models to capture. Although the Quantum Graph Transformer (QGT) offers a hybrid quantum–classical perspective, its reliance on fully connected graphs and less flexible attention mechanisms limits its effectiveness. To overcome these issues, we introduce the Adaptive Quantum-Inspired Graph Transformer (AQGT), which incorporates an adaptive semantic graph construction method that forms sparse yet informative graphs, along with a quantum-inspired message passing unit for more efficient feature aggregation. AQGT processes text through a multi-layer hybrid architecture that dynamically models semantic structure and enhances node interactions through principled message passing. Experiments on multiple sentiment classification benchmarks show that AQGT achieves consistently stronger performance than classical models and the original QGT. Ablation studies validate the importance of the adaptive graph and message passing components. AQGT further displays good sample efficiency, stable behavior across hyperparameters, and strong qualitative performance in handling nuanced sentiment phenomena such as sarcasm and implicit polarity. These findings demonstrate AQGT’s capability as a robust and expressive model for complex sentiment analysis.
Transformers are increasingly employed for graph data, demonstrating competitive performance in diverse tasks. To incorporate graph information into these models, it is essential to enhance node and edge features with positional encodings. In this work, we propose novel families of positional encodings tailored for graph transformers. These encodings leverage the long-range correlations inherent in quantum systems, which arise from mapping the topology of a graph onto interactions between qubits in a quantum computer. Our inspiration stems from the recent advancements in quantum processing units, which offer computational capabilities beyond the reach of classical hardware. We prove that some of these quantum features are theoretically more expressive for certain graphs than the commonly used relative random walk probabilities. Empirically, we show that the performance of state-of-the-art models can be improved on standard benchmarks and large-scale datasets by computing tractable versions of quantum features. Our findings highlight the potential of leveraging quantum computing capabilities to potentially enhance the performance of transformers in handling graph data.
Graphs provide a natural language for relational data in chemistry, biology and optimisation. Graph neural networks (GNNs) have driven much of the recent progress in learning from such data through message passing, a single primitive that generalises convolution and attention. Quantum counterparts have been proposed, but with limited connection to message passing and few guarantees on performance or scalability. More broadly, the trainability of variational quantum circuits is a recognised bottleneck for their wide applicability, and pre-training has emerged as one way to address it. Yet for a quantum model to be useful, it must offer expressivity guarantees along with demonstrable scalability. Here we show how a quantum graph neural network can be built to perform message passing, to be permutation equivariant, and to sit at a chosen level of the Weisfeiler-Leman hierarchy, the standard measure of how finely a model can tell graphs apart. We show that, as for classical GNNs, the training can be done first on small graph instances, allowing for a pre-training that can mitigate usual training issues, and its output can be read out at a cost that stays low as the graph grows. We validate the framework in large-scale simulations of up to 56 qubits across three datasets, on synthetic graphs that ordinary message passing cannot separate, on molecular property prediction, and on the travelling salesperson problem. Our framework opens a path for near-term quantum algorithms with theoretical guarantees and practical scalability, bringing the principles of graph learning into quantum circuit design.