Entanglement Verification with Deep Semi-supervised Machine Learning

TL;DR

This paper introduces a deep semi-supervised machine learning approach for efficient and scalable quantum entanglement verification, especially in high-dimensional and multipartite systems, outperforming traditional methods.

Contribution

It develops a novel semi-supervised learning model based on FixMatch and Pseudo-Label techniques, incorporating data augmentation strategies tailored for quantum states.

Findings

The model achieves higher accuracy than traditional supervised methods.

It demonstrates good generalization on complex quantum states.

The approach is effective with limited labeled data.

Abstract

Quantum entanglement lies at the heart in quantum information processing tasks. Although many criteria have been proposed, efficient and scalable methods to detect the entanglement of generally given quantum states are still not available yet, particularly for high-dimensional and multipartite quantum systems. Based on FixMatch and Pseudo-Label method, we propose a deep semi-supervised learning model with a small portion of labeled data and a large portion of unlabeled data. The data augmentation strategies are applied in this model by using the convexity of separable states and performing local unitary operations on the training data. We verify that our model has good generalization ability and gives rise to better accuracies compared to traditional supervised learning models by detailed examples.