Abstract Variational quantum circuits (VQC) lie at the forefront of quantum machine learning research. Still, the use of quantum networks for real data processing remains challenging as the number of available qubits cannot accommodate a large dimensionality of data—if the usual angle encoding scenario is used. To achieve dimensionality reduction, Principal Component Analysis is routinely applied as a pre-processing method before the embedding of the classical features on qubits. In this work, we propose an alternative method which reduces the dimensionality of a given dataset by taking into account the specific quantum embedding that comes after. This method aspires to make quantum machine learning with VQCs more versatile and effective on datasets of high dimension. At a second step, we propose a quantum-inspired classical autoencoder model which can be used to encode information in low latent spaces. The power of our proposed models is exhibited via numerical tests. We show that our targeted dimensionality reduction method considerably boosts VQC’s performance, and we also identify cases for which the second model outperforms classical autoencoders in terms of reconstruction loss.
Abstract Variational quantum circuits (VQC) lie at the forefront of quantum machine learning research. Still, the use of quantum networks for real data processing remains challenging as the number of available qubits cannot accommodate a large dimensionality of data—if the usual angle encoding scenario is used. To achieve dimensionality reduction, Principal Component Analysis is routinely applied as a pre-processing method before the embedding of the classical features on qubits. In this work, we propose an alternative method which reduces the dimensionality of a given dataset by taking into account the specific quantum embedding that comes after. This method aspires to make quantum machine learning with VQCs more versatile and effective on datasets of high dimension. At a second step, we propose a quantum-inspired classical autoencoder model which can be used to encode information in low latent spaces. The power of our proposed models is exhibited via numerical tests. We show that our targeted dimensionality reduction method considerably boosts VQC’s performance, and we also identify cases for which the second model outperforms classical autoencoders in terms of reconstruction loss.
Intrusion detection remains a critical challenge in cybersecurity, particularly when dealing with high-dimensional data. In this work, we propose a hybrid quantum machine learning model that integrates a Quantum Autoencoder (QAE) for dimensionality reduction with a Quantum Neural Network (QNN) classifier. The QAE compresses input features into latent states without relying on classical methods such as Principal Component Analysis (PCA), preserving quantum-relevant information. These latent states are then classified using a Variational Quantum Circuit implemented with Qiskit. We systematically evaluated different ansatz architectures and hyperparameters on the NSL-KDD dataset. The best configuration, an EstimatorQNN with EfficientSU2 ansatz (4 repetitions), achieved an F1-score of 0.767, with balanced recall (0.70) and precision (0.84). These results highlight the potential of quantum-enhanced models for addressing the scalability challenges of intrusion detection, representing a step toward applying High-Performance Computing principles to cybersecurity.
One key step in performing quantum machine learning (QML) on noisy intermediate-scale quantum (NISQ) devices is the dimension reduction of the input data prior to their encoding. Traditional principle component analysis (PCA) and neural networks have been used to perform this task; however, the classical and quantum layers are usually trained separately. A framework that allows for a better integration of the two key components is thus highly desirable. Here we introduce a hybrid model combining the quantum-inspired tensor networks (TN) and the variational quantum circuits (VQC) to perform supervised learning tasks, which allows for an end-to-end training. We show that a matrix product state based TN with low bond dimensions performs better than PCA as a feature extractor to compress data for the input of VQCs in the binary classification of MNIST dataset. The architecture is highly adaptable and can easily incorporate extra quantum resource when available.
Large language and sentence-embedding models provide rich semantic representations, but their high dimensionality poses a challenge for near-term quantum machine learning (QML), where quantum circuits can process only a limited number of input features. We investigate a hybrid quantum-classical pipeline that transforms high-dimensional sentence embeddings into compact representations for variational quantum classification. The workflow combines a pretrained sentence-embedding model, dimensionality reduction, angle encoding, a variational quantum circuit (VQC), and a classical decision layer. We systematically compare principal component analysis (PCA), neighborhood components analysis (NCA), and linear discriminant analysis (LDA), covering both unsupervised and supervised dimensionality reduction. Using the TREC question-classification dataset, we study the relationship between representation dimensionality, information retention, qubit count, and classification performance. Preliminary PCA experiments reveal a strong information bottleneck: reducing 768-dimensional embeddings to 3, 4, 5, and 8 dimensions retains about 8.2%, 10.2%, 11.9%, and 16.4% of the variance, with corresponding classification accuracies of 50.3%, 51.2%, 57.9%, and 63.4%. In contrast, supervised reduction is substantially more efficient. LDA reaches 85.3% accuracy and NCA reaches 83.1% using only 5 dimensions, under a leakage-free cross-validation protocol, compared with 85.1% for a full 384-dimensional classical baseline. These results indicate that supervised dimensionality reduction can preserve task-relevant information far more effectively than variance-based compression, making compact representations a promising route toward practical hybrid quantum-classical NLP models.
Quantum neural networks (QNNs) offer a promising avenue for machine learning by leveraging quantum computation, but practical QNN models are constrained by the low dimensionality of the input data they can handle. This paper proposes a hybrid quantum-classical neural network architecture that incorporates principal component analysis (PCA) for dimensionality reduction and variational quantum circuits (VQC) for quantum feature encoding. Focusing on the Wisconsin Diagnostic Breast Cancer dataset (569 instances, 30 features) as a representative biomedical classification task, in this work, we design hybrid quantum-classical neural network (QNN) models using 5-qubit and 10-qubit quantum circuits. For comparison, we use classical baseline identical to the downstream head but without the VQC+measurement. The preprocessed inputs feed the classifier head directly; only the input layer dimension is adjusted to the number of features. The 5-qubit hybrid model is evaluated under two conditions: with and without principal component analysis (PCA) applied as a preprocessing step to investigate the effect of dimensionality reduction on model performance. In contrast, the 10 -qubit hybrid model is evaluated without PCA, directly processing the input features to explore its capacity to handle higher-dimensional data within the quantum circuit. Performance is measured in terms of classification accuracy, precision, recall, and F1-score. We evaluate the model’s robustness by injecting noise into the training data, finding that the PCA-enhanced hybrid QNN maintains competitive accuracy and resilience under perturbation. This study highlights the potential of PCA-driven variational quantum encodings to enhance QNNs for reliable biomedical data classification.
We combine classical and quantum Machine Learning (ML) techniques to effectively analyze long time-series data acquired during experiments. Specifically, we demonstrate that replacing a deep classical neural network with a thoughtfully designed Variational Quantum Circuit (VQC) in an ML pipeline for multiclass classification of time-series data yields the same classification performance, while significantly reducing the number of trainable parameters. To achieve this, we use a VQC based on a single qudit, and encode the classical data into the VQC via a trainable hybrid autoencoder which has been recently proposed as embedding technique. Our results highlight the importance of tailored data pre-processing for the circuit and show the potential of qudit-based VQCs.
Embedding of n-dimensional data in quantum space is an essential component in quantum computing realm. This research area is quite challenging with limited computational resources and complex quantum architecture. To overcome these problems, quantum approaches have been integrated with classical neural network. This hybrid model encodes the features using both angle encoding and amplitude encoding over quantum hilbert space, which is then processed through a Variational Quantum Circuit (VQC). These embedded features are fed to the classical neural network that enhances the performance of the traditional methods. A synthetic barcode and stripes (BAS) dataset was created for the verification of the proposed model. The results show that classical optimization methods, specifically gradient descent with momentum, achieve an accuracy of 82.38% for 4×4 data which is a significant improvement over existing researches that are limited to lower-dimensional data embedding.