Quantum Walk Inspired Neural Networks for Graph-Structured Data
Quantum Physics
2018-06-18 v2
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.
Cite
@article{arxiv.1801.05417,
title = {Quantum Walk Inspired Neural Networks for Graph-Structured Data},
author = {Stefan Dernbach and Arman Mohseni-Kabir and Siddharth Pal and Don Towsley and Miles Gepner},
journal= {arXiv preprint arXiv:1801.05417},
year = {2018}
}
Comments
In submission to NIPS 2018