Quantum Machine Learning via Contrastive Training

TL;DR

This paper presents a self-supervised contrastive training method for quantum machine learning that improves image classification accuracy on quantum hardware, especially with limited labeled data, by learning invariances from unlabeled quantum data.

Contribution

It introduces a novel quantum contrastive pretraining approach executed on hardware, reducing reliance on labeled data and enhancing classification performance.

Findings

Pretraining on quantum hardware improves classification accuracy.

The learned invariances generalize beyond pretraining samples.

Performance gains are significant with limited labeled data.

Abstract

Quantum machine learning (QML) has attracted growing interest with the rapid parallel advances in large-scale classical machine learning and quantum technologies. Similar to classical machine learning, QML models also face challenges arising from the scarcity of labeled data, particularly as their scale and complexity increase. Here, we introduce self-supervised pretraining of quantum representations that reduces reliance on labeled data by learning invariances from unlabeled examples. We implement this paradigm on a programmable trapped-ion quantum computer, encoding images as quantum states. In situ contrastive pretraining on hardware yields a representation that, when fine-tuned, classifies image families with higher mean test accuracy and lower run-to-run variability than models trained from random initialization. Performance improvement is especially significant in regimes with limited labeled training data. We show that the learned invariances generalize beyond the pretraining image samples. Unlike prior work, our pipeline derives similarity from measured quantum overlaps and executes all training and classification stages on hardware. These results establish a label-efficient route to quantum representation learning, with direct relevance to quantum-native datasets and a clear path to larger classical inputs.