Bosonic Random Walk Networks for Graph Learning
This work addresses the problem of enhancing graph learning for researchers by exploring a novel quantum-inspired approach, representing an incremental step in GNN development.
This paper explores the application of multi-particle quantum walks for diffusing information across graphs, aiming to improve graph learning tasks. The model learns operators governing quantum random walker dynamics, demonstrating effectiveness on classification and regression tasks.
The development of Graph Neural Networks (GNNs) has led to great progress in machine learning on graph-structured data. These networks operate via diffusing information across the graph nodes while capturing the structure of the graph. Recently there has also seen tremendous progress in quantum computing techniques. In this work, we explore applications of multi-particle quantum walks on diffusing information across graphs. Our model is based on learning the operators that govern the dynamics of quantum random walkers on graphs. We demonstrate the effectiveness of our method on classification and regression tasks.