Bosonic Random Walk Networks for Graph Learning
arXiv:2101.00082
Abstract
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.
References in corpus (11)
- Quantum Machine Learning
- Spectral Networks and Locally Connected Networks on Graphs
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
- Universal computation by quantum walk
- Two-particle quantum walks applied to the graph isomorphism problem
- Quantum walks on general graphs
- Multi-walker discrete time quantum walks on arbitrary graphs, their properties, and their photonic implementation
- Quantum Logic with Interacting Bosons in 1D
- Two-walker discrete-time quantum walks on the line with percolation
- Quantum walk on distinguishable non-interacting many-particles and indistinguishable two-particle
- Quantum Walk Inspired Neural Networks for Graph-Structured Data