Quantum Walk Inspired Neural Networks for Graph-Structured Data
arXiv:1801.05417
Abstract
In recent years, new neural network architectures designed to operate on graph-structured data have pushed the state-of-the-art in the field. A large set of these architectures utilize a form of classical random walks to diffuse information. We propose quantum walk neural networks (QWNN), a novel graph neural network architecture based on quantum random walks, the quantum parallel to classical random walks. A QWNN learns a quantum walk on a graph to construct a diffusion operator which can then be applied to graph-structured data. We demonstrate the use of QWNNs on a variety of prediction tasks on graphs involving temperature, biological, and molecular datasets.
arXiv commentIn submission to NIPS 2018
References in corpus (11)
- Semi-Supervised Classification with Graph Convolutional Networks
- Quantum Machine Learning
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
- Quantum Computation and Decision Trees
- A Quantum Random Walk Search Algorithm
- Universal computation by quantum walk
- Diffusion-Convolutional Neural Networks
- Quantum walks on general graphs
- Quantum walk-based search and centrality
- Multi-walker discrete time quantum walks on arbitrary graphs, their properties, and their photonic implementation
- Machine learning \& artificial intelligence in the quantum domain