Graph-Based Bayesian Optimization for Quantum Circuit Architecture Search with Uncertainty Calibrated Surrogates

2025-12-10

AI Summary

Quantum machine learning (QML) faces significant challenges in practical deployment on cybersecurity datasets (e.g., NF-ToN-IoT-V2), particularly due to the difficulty of designing problem-tailored quantum circuits manually. Method: We propose the first automated search framework for graph-structured quantum circuits, integrating a graph neural network (GNN) surrogate model with uncertainty-calibrated Bayesian optimization. Circuits are encoded as graphs, and Monte Carlo Dropout quantifies surrogate uncertainty to guide expected improvement sampling. The framework further incorporates noise-robustness evaluation and an interpretable, reproducible circuit extraction pipeline. Contribution/Results: The discovered circuits exhibit lower complexity and achieve classification accuracy competitive with or superior to classical MLPs, random search, and greedy GNN baselines. Crucially, they demonstrate strong robustness under five realistic hardware noise models—amplitude damping, phase damping, thermal relaxation, depolarizing noise, and readout errors—validating practical viability for near-term quantum devices.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Quantum circuit design is a key bottleneck for practical quantum machine learning on complex, real-world data. We present an automated framework that discovers and refines variational quantum circuits (VQCs) using graph-based Bayesian optimization with a graph neural network (GNN) surrogate. Circuits are represented as graphs and mutated and selected via an expected improvement acquisition function informed by surrogate uncertainty with Monte Carlo dropout. Candidate circuits are evaluated with a hybrid quantum-classical variational classifier on the next generation firewall telemetry and network internet of things (NF-ToN-IoT-V2) cybersecurity dataset, after feature selection and scaling for quantum embedding. We benchmark our pipeline against an MLP-based surrogate, random search, and greedy GNN selection. The GNN-guided optimizer consistently finds circuits with lower complexity and competitive or superior classification accuracy compared to all baselines. Robustness is assessed via a noise study across standard quantum noise channels, including amplitude damping, phase damping, thermal relaxation, depolarizing, and readout bit flip noise. The implementation is fully reproducible, with time benchmarking and export of best found circuits, providing a scalable and interpretable route to automated quantum circuit discovery.

Problem

• Automated variational quantum circuit design for quantum machine learning
• Graph-based Bayesian optimization with uncertainty-calibrated GNN surrogates
• Robust circuit discovery under quantum noise for cybersecurity classification

Innovation

• Graph-based Bayesian optimization with GNN surrogate
• Uncertainty calibration via Monte Carlo dropout
• Hybrid quantum-classical evaluation on cybersecurity dataset