GAT-QNN: Genetic Algorithm-Based Training of Hybrid Quantum Neural Networks

TL;DR

GAT-QNN introduces a genetic algorithm framework for training hybrid quantum neural networks, optimizing circuit architectures and improving classification accuracy across different quantum backends.

Contribution

It presents a novel GA-based method for macroCircuit training and microCircuit selection, addressing noise and heterogeneity in quantum hardware deployment.

Findings

Achieved 22-23% test accuracy gains on MNIST classification.

Enabled backend-aware microCircuit selection without retraining.

Reduced computational resources by deploying smaller microCircuits.

Abstract

Hybrid Quantum Neural Networks (HQNNs) combine classical learning with parameterized quantum circuits, but their practical performance is often limited by (i) the noise of Noisy Intermediate-Scale Quantum (NISQ) devices and (ii) the large, discrete design space of quantum circuit architectures. Moreover, HQNNs are commonly trained using a fixed circuit and a single backend, even though deployment frequently targets heterogeneous backends where compilation and execution characteristics may differ. To address these challenges, we propose GAT-QNN, a genetic algorithm (GA)-based framework that trains a macroCircuit (search space) by iteratively sampling microCircuits (subcircuits), training them, and reintegrating their learned parameters into the macroCircuit. After training, we run an independent GA-driven inference stage that evaluates candidate microCircuits using the trained macroCircuit weights and selects top-performing architectures for deployment. This two-stage approach enables backend-aware microCircuit selection without retraining each candidate architecture and can also reduce computational resources (gate count) by deploying smaller microCircuits derived from the macroCircuit. We validate the approach on MNIST classification (four classes) and report consistent 22-23% test accuracy gains for GA-driven inference across multiple backends.