Benchmarking data encoding methods in Quantum Machine Learning

TL;DR

This paper benchmarks various data encoding methods in Quantum Machine Learning, highlighting their impact on model performance and providing insights into selecting suitable encodings for different datasets.

Contribution

It systematically compares common quantum data encoding techniques across multiple datasets, offering guidance for optimal encoding choices in QML.

Findings

Certain encoding methods outperform others depending on the dataset

Encoding choice significantly influences QML model accuracy

Benchmark results provide a reference for future QML encoding strategies

Abstract

Data encoding plays a fundamental and distinctive role in Quantum Machine Learning (QML). While classical approaches process data directly as vectors, QML may require transforming classical data into quantum states through encoding circuits, known as quantum feature maps or quantum embeddings. This step leverages the inherently high-dimensional and non-linear nature of Hilbert space, enabling more efficient data separation in complex feature spaces that may be inaccessible to classical methods. This encoding part significantly affects the performance of the QML model, so it is important to choose the right encoding method for the dataset to be encoded. However, this choice is generally arbitrary, since there is no "universal" rule for knowing which encoding to choose based on a specific set of data. There are currently a variety of encoding methods using different quantum logic gates. We studied the most commonly used types of encoding methods and benchmarked them using different datasets.