GQWformer: A Quantum-based Transformer for Graph Representation Learning

TL;DR

GQWformer introduces a quantum-inspired graph transformer that leverages quantum walks to encode structural information, enhancing graph representation learning by integrating quantum states as inductive biases.

Contribution

The paper presents a novel quantum-based approach for graph transformers, incorporating quantum walks to encode structural biases and improve attention mechanisms in GNNs.

Findings

GQWformer outperforms existing graph classification methods on multiple datasets.

Quantum walk-based structural encoding enhances attention quality in graph transformers.

The approach demonstrates the potential of quantum techniques in advancing GNN performance.

Abstract

Graph Transformers (GTs) have demonstrated significant advantages in graph representation learning through their global attention mechanisms. However, the self-attention mechanism in GTs tends to neglect the inductive biases inherent in graph structures, making it chanllenging to effectively capture essential structural information. To address this issue, we propose a novel approach that integrate graph inductive bias into self-attention mechanisms by leveraging quantum technology for structural encoding. In this paper, we introduce the Graph Quantum Walk Transformer (GQWformer), a groundbreaking GNN framework that utilizes quantum walks on attributed graphs to generate node quantum states. These quantum states encapsulate rich structural attributes and serve as inductive biases for the transformer, thereby enabling the generation of more meaningful attention scores. By subsequently incorporating a recurrent neural network, our design amplifies the model's ability to focus on both local and global information. We conducted comprehensive experiments across five publicly available datasets to evaluate the effectiveness of our model. These results clearly indicate that GQWformer outperforms existing state-of-the-art graph classification algorithms. These findings highlight the significant potential of integrating quantum computing methodologies with traditional GNNs to advance the field of graph representation learning, providing a promising direction for future research and applications.