QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks

TL;DR

QuanGCN introduces a noise-adaptive quantum graph convolutional network that enhances robustness against quantum device noise, achieving competitive or superior performance to classical algorithms on benchmark datasets.

Contribution

This work pioneers the application of quantum graph neural networks with noise mitigation techniques for real-world graph classification tasks.

Findings

QuanGCN performs comparably or better than classical algorithms.

The method is effective on both simulators and real quantum hardware.

Noise mitigation improves quantum GCN robustness.

Abstract

Quantum neural networks (QNNs), an interdisciplinary field of quantum computing and machine learning, have attracted tremendous research interests due to the specific quantum advantages. Despite lots of efforts developed in computer vision domain, one has not fully explored QNNs for the real-world graph property classification and evaluated them in the quantum device. To bridge the gap, we propose quantum graph convolutional networks (QuanGCN), which learns the local message passing among nodes with the sequence of crossing-gate quantum operations. To mitigate the inherent noises from modern quantum devices, we apply sparse constraint to sparsify the nodes' connections and relieve the error rate of quantum gates, and use skip connection to augment the quantum outputs with original node features to improve robustness. The experimental results show that our QuanGCN is functionally comparable or even superior than the classical algorithms on several benchmark graph datasets. The comprehensive evaluations in both simulator and real quantum machines demonstrate the applicability of QuanGCN to the future graph analysis problem.