Feature Prediction in Quantum Graph Recurrent Neural Networks with Applications in Information Hiding

TL;DR

This paper explores the use of Quantum Graph Recurrent Neural Networks (QGRNNs) for feature prediction and information hiding in classical graph-structured data, demonstrating high accuracy and robustness in both tasks.

Contribution

It introduces the application of QGRNNs to classical data, showing their effectiveness in feature reconstruction and secure message embedding with high accuracy.

Findings

QGRNN achieves high feature reconstruction accuracy.

QGRNN maintains high message retrieval accuracy with increasing complexity.

QGRNN demonstrates scalability and robustness for classical data and information hiding.

Abstract

Graphs are a fundamental representation of complex, nonlinear structured data across various domains, including social networks and quantum systems. Quantum Graph Recurrent Neural Networks (QGRNNs) have been proposed to model quantum dynamics in graph-based quantum systems, but their applicability to classical data remains an open problem. In this paper, we leverage QGRNNs to process classical graph-structured data. In particular, we demonstrate how QGRNN can reconstruct node features in classical datasets. Our results show that QGRNN achieves high feature reconstruction accuracy, leading to near-perfect classification. Furthermore, we propose an information hiding technique based on our QGRNN, where messages are embedded into a graph, then retrieved under certain conditions. We assess retrieval accuracy for different dictionary sizes and message lengths, showing that QGRNN maintains high retrieval accuracy, with minor degradation as complexity increases. These findings demonstrate the scalability and robustness of QGRNNs for both classical data processing and secure information hiding, paving the way for quantum-enhanced feature extraction, privacy-preserving computations, and quantum steganography.