Quantum Graph Transformer for NLP Sentiment Classification

2025-06-09

AI Summary

To address the challenges of modeling structured data, excessive parameter counts, and low sample efficiency in natural language processing, this paper proposes the Quantum Graph Transformer (QGT)—the first architecture to embed parameterized quantum circuits into a graph message-passing framework, thereby realizing a quantum-enhanced self-attention mechanism. By synergistically integrating quantum computation with graph neural networks, QGT significantly reduces trainable parameters while improving generalization and few-shot learning performance. Empirical evaluation across five sentiment classification benchmarks demonstrates that QGT consistently outperforms existing quantum NLP models. Compared to classical graph transformers, QGT achieves average accuracy gains of 5.42% on real-world data and 4.76% on synthetic data. Notably, on the Yelp dataset, QGT attains comparable performance using only 50% of the labeled samples, validating its high sample efficiency and practical applicability.

Technology Category

• Machine Learning: Quantum Machine Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search

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.

Problem

• Develops Quantum Graph Transformer for NLP sentiment classification
• Reduces trainable parameters with quantum self-attention mechanism
• Improves accuracy and sample efficiency in QNLP models

Innovation

• Hybrid graph-based architecture with quantum self-attention
• Parameterized quantum circuits reduce trainable parameters
• Improved accuracy and sample efficiency in NLP