Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Studies in computational intelligence

Quantum Walk Neural Networks for Graph-Structured Data

Stefan Dernbach, Arman Mohseni-Kabir, Siddharth Pal, Don Towsley

Published Dec 4, 2018• 11 citations
Publisher
DOI
10.1007/978-3-030-05414-4_15

Related papers

Bosonic Random Walk Neural Networks for Graph Learning

Shiv Shankar Shankar, Don Towsley

Studies in computational intelligence•Jan 1, 2022•0 citations

Learnability of a hybrid quantum-classical neural network for graph-structured quantum data

Yanying Liang, Si-Le Tang, Yi Zhu +2 more

arXiv:2401.15665•Quantum Information Processing•Nov 24, 2025•0 citations

Realization of classification tasks via complex graph neural networks based on the continuous-time quantum walk

Jiaqi Sun, Zhihao Bian

Physical Review A•Jan 21, 2026•0 citations

Quantum Walk Inspired Neural Networks for Graph-Structured Data

Stefan Dernbach, Arman Mohseni-Kabir, Siddharth Pal +2 more

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:1801.05417•Jan 16, 2018•2 citations

Quantum walk neural networks with feature dependent coins

Stefan Dernbach, Arman Mohseni-Kabir, Siddharth Pal +2 more

Abstract Recent neural networks designed to operate on graph-structured data have proven effective in many domains. These graph neural networks often diffuse information using the spatial structure of the graph. We propose a quantum walk neural network that learns a diffusion operation that is not only dependent on the geometry of the graph but also on the features of the nodes and the learning task. A quantum walk neural network is based on learning the coin operators that determine the behavior of quantum random walks, the quantum parallel to classical random walks. We demonstrate the effectiveness of our method on multiple classification and regression tasks at both node and graph levels.

Applied Network Science•Sep 23, 2019•24 citations

Quantum-Inspired Neural Networks

Moolchand Sharma, Nebojša Bačanin, Tarik Ahmed Rashid

CRC Press eBooks•May 20, 2026•0 citations
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.
Abstract Recent neural networks designed to operate on graph-structured data have proven effective in many domains. These graph neural networks often diffuse information using the spatial structure of the graph. We propose a quantum walk neural network that learns a diffusion operation that is not only dependent on the geometry of the graph but also on the features of the nodes and the learning task. A quantum walk neural network is based on learning the coin operators that determine the behavior of quantum random walks, the quantum parallel to classical random walks. We demonstrate the effectiveness of our method on multiple classification and regression tasks at both node and graph levels.