.png){kind=icon}
.png){kind=icon}
Return
Enhancing graph learning with quantum structural encoding
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.132054.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph Transformers (GTs) have demonstrated significant advantages in graph representation learning through their global attention mechanisms. However, the self-attention mechanism in vanilla GTs tends to neglect the inductive biases inherent in graph structures, making it challenging to effectively capture essential structural information. To address this issue, we propose a novel approach that integrates graph-inductive bias into self-attention mechanisms by leveraging quantum technology for structural encoding. In this paper, we introduce the Graph Quantum Walk Neural Network (GQWNN), 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 in five publicly available datasets to evaluate the effectiveness of our model. These results clearly indicate that GQWNN 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.