We propose a Hybrid classical-quantum Autoencoder (HAE) model, which is a synergy of a classical autoencoder (AE) and a parametrized quantum circuit (PQC) that is inserted into its bottleneck. The PQC augments the latent space, on which a standard outlier detection method is applied to search for anomalous data points within a classical dataset. Using this model and applying it to both standard benchmarking datasets, and a specific use-case dataset which relates to predictive maintenance of gas power plants, we show that the addition of the PQC leads to a performance enhancement in terms of precision, recall, and F1 score. Furthermore, we probe different PQC Ans\"atze and analyse which PQC features make them effective for this task.
Cite
@article{arxiv.2112.08869,
title = {Hybrid Classical-Quantum Autoencoder for Anomaly Detection},
author = {Alona Sakhnenko and Corey O'Meara and Kumar J. B. Ghosh and Christian B. Mendl and Giorgio Cortiana and Juan Bernabé-Moreno},
journal= {arXiv preprint arXiv:2112.08869},
year = {2022}
}