Discovering Data Encoding Strategies for Quantum-Classical Neural Networks Using Monte Carlo Tree Search

TL;DR

This paper uses Monte Carlo Tree Search to discover effective data encoding strategies for quantum-classical neural networks, improving performance on medical imaging tasks and providing insights into encoding effectiveness.

Contribution

Introduces a novel application of MCTS for optimizing data encodings in QML, offering a practical method and new understanding of encoding performance factors.

Findings

Discovered encoding circuits outperform common strategies.

Effective rank of feature maps correlates with encoding performance.

Entanglement and Fourier metrics offer limited predictive value.

Abstract

Quantum machine learning (QML) has attracted considerable research interest, yet whether it offers practical benefits over classical approaches remains an open question. The choice of data encoding significantly influences QML performance, but why certain encodings outperform others remains poorly understood. We employ Monte Carlo Tree Search (MCTS) to discover optimal data encoding circuits for a quantum-classical convolutional neural network (QCCNN) combining a non-variational quantum block for feature extraction with a classical classifier. Evaluating on two medical imaging datasets, the discovered circuits outperform commonly used encoding strategies while showing competitive results compared to purely classical counterparts. We further analyze metrics to identify predictors of encoding performance. Entanglement capability and Fourier decomposition provide minimal insight, whereas the effective rank of the feature maps exhibits meaningful correlation and can serve as a threshold criterion to accelerate the search for high-performing encodings. Our findings provide both a practical method for encoding discovery and new insights into what makes data encodings effective in QML.