Analog Quantum Asynchronous Event-Based Graph Neural Network

2026-06-09

AI Summary

Traditional methods struggle to efficiently model the sparse, high-temporal-resolution data generated by event cameras. This work presents the first native implementation of an event-based graph neural network on a neutral-atom quantum processor, where asynchronous event streams are encoded as nodes in an atomic array. Programmable Rydberg interactions are leveraged to simulate continuous Hamiltonian dynamics, enabling quantum-parallel message passing. By training the simulated Hamiltonian parameters via hybrid quantum–classical optimization, the approach preserves data sparsity while demonstrating potential for computational acceleration and enhanced accuracy.

Abstract

Asynchronous, event-based graph neural networks (AEGNNs) have recently emerged as an efficient paradigm for processing the sparse and high-temporal-resolution data from event cameras. In this paper, we propose quantum analog AEGNNs (QA-AEGNNs), a novel framework to implement an AEGNN on a neutral-atom quantum computer. Neutral-atom quantum processors offer a programmable analog quantum computing platform based on controllable Rydberg-atom interactions. To this end, we map the streaming event data to an array of trapped neutral atoms, where each atom represents a graph node (event) and is positioned such that geometric proximity reflects the spatio-temporal neighborhood of events. The native Rydberg Hamiltonian of the quantum processor is programmed to mirror the message-passing computations of the AEGNN, with atomic qubit states serving as node feature embeddings and inter-atom interactions realizing graph edges. Furthermore, we propose a hybrid quantum-classical training scheme in which the analog Hamiltonian parameters (e.g., laser pulse amplitudes and detunings) are optimized using classical feedback to learn the quantum AEGNN model from data. Our approach leverages the continuous Hamiltonian dynamics and massive parallelism of neutral-atom quantum systems to natively execute event-based graph computations with potential accuracy improvements

Problem

• asynchronous event-based graph neural networks
• event cameras
• neutral-atom quantum computing
• sparse temporal data
• graph neural networks

Innovation

• quantum analog computing
• neutral-atom quantum processor
• event-based graph neural network
• Rydberg Hamiltonian
• hybrid quantum-classical training