A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction

2026-05-20

AI Summary

Existing temporal graph models struggle to effectively capture high-frequency, concurrent node-edge interactions in large-scale dynamic graphs, which limits their link prediction performance. This work proposes a hybrid quantum-classical architecture that maps node interaction features into quantum states via adaptive amplitude encoding and integrates them with a temporal graph network backbone. The framework selectively updates quantum embeddings based on nodal temporal activity, preserving stable representations while emphasizing structural evolution. By introducing an activity-aware adaptive update mechanism and noise-aware quantum inference, the method significantly reduces redundant re-encoding and enhances the efficiency of temporal representation learning. Evaluated on five benchmark datasets, the model achieves strong performance in both link prediction and ranking tasks. Ablation studies confirm the effectiveness of the quantum embedding module and the adaptive updating strategy, demonstrating the feasibility of recent quantum-assisted learning approaches for dynamic graph modeling.

Abstract

Dynamic link prediction is important for modeling evolving interactions in complex systems, including social, communication, financial, and transportation networks. Classical temporal graph models capture sequential dependencies, but they may struggle to represent concurrent and rapidly changing node-edge interactions in large dynamic graphs. We propose A2QTGN (Adaptive Amplitude Quantum-Integrated Temporal Graph Network), a hybrid quantum-classical framework that combines adaptive amplitude encoding with a Temporal Graph Network backbone. The proposed mechanism represents node interaction features as quantum states and selectively refreshes amplitude embeddings based on temporal activity, preserving stable node states while emphasizing meaningful structural changes. This design reduces unnecessary quantum re-encoding and improves temporal representation for link prediction. Experiments on five Temporal Graph Benchmark datasets show that A2QTGN achieves strong predictive and ranking performance across diverse dynamic graphs. Ablation studies confirm the importance of both the quantum embedding module and the adaptive update strategy, while hardware-aware inference using a noisy backend and limited real-device execution supports the feasibility of near-term quantum-assisted temporal graph learning.

Problem

• dynamic link prediction
• temporal graph
• quantum machine learning
• adaptive encoding
• complex networks

Innovation

• quantum-classical hybrid
• adaptive amplitude encoding
• temporal graph network
• dynamic link prediction
• quantum embedding