Anomaly Detection Based on Quantum Autoencoder

Quantum autoencoder (QAE) is a key tool in quantum machine learning and can be applied to areas such as dimensionality reduction and feature extraction [1]. Anomaly detection identifies deviations from normal patterns, which is crucial yet challenging due to the need to detect risks while minimizing...

Full description

Saved in:
Bibliographic Details
Published in:Conference on Lasers & Electro-Optics Europe & International Quantum Electronics Conference (Online) p. 1
Main Authors: Li, Siqi, Zhang, Zikun, Zhu, Xun, Ou, Yanni, Xu, Kun
Format: Conference Proceeding
Language:English
Published: IEEE 23.06.2025
Subjects:
Adaptive optics
Anomaly detection
Autoencoders
Decoding
Feature extraction
Neural networks
Optical computing
Optical network units
Quantum state
Training
ISSN:2833-1052
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Quantum autoencoder (QAE) is a key tool in quantum machine learning and can be applied to areas such as dimensionality reduction and feature extraction [1]. Anomaly detection identifies deviations from normal patterns, which is crucial yet challenging due to the need to detect risks while minimizing false positives [2]. We propose a QAE-based anomaly detection scheme using an optical quantum neural network. Figure 1 (A) shows the basic structure of the QAE: the encoder compresses the input quantum state into a low-dimensional latent space, and the decoder reconstructs the original quantum state from the latent space. QAE-based anomaly detection works by learning the low-dimensional features of normal data and minimizing its reconstruction error. Normal data can be well reconstructed, while anomalous data exhibits a larger reconstruction error. When the reconstruction error of test data exceeds a set threshold, it is classified as anomalous. We constructed the QAE using an optical quantum neural network consisting of 50:50 beam splitters and controllable phase shifters [3]. Due to the unitary matrix property, only the encoder needs to be trained, and the decoder is simply the conjugate transpose of the encoder. To compress an N-dimensional quantum state \rho into {K} dimensions, efficient compression can be achieved by minimizing the expectation value of the projection onto the trash state, given by C(\theta,\phi)=Tr\left(PU(\theta,\phi)\rho U^+(\theta,\phi)\right) [4]. Here, P=(I_{K}\oplus\vert 0\rangle^{\otimes N-K}\langle 0\vert ^{\otimes(N-K)}) represents the projection onto the trash state, I_{K} is the K-dimensional identity matrix, \vert 0\rangle^{\otimes(N-K)}\text{is} the trash state, Tr denotes the trace, U(\theta,\phi) is the encoder with adjustable parameters, and U\dagger(\theta_,\phi) is the decoder. We only need to train the encoder during the training process, and the decoder is simply its conjugate transpose.
ISSN:2833-1052
DOI:10.1109/CLEO/Europe-EQEC65582.2025.11110982