Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2311.05559 · International Conference on Agents and Artificial Intelligence (ICAART)

Disentangling Quantum and Classical Contributions in Hybrid Quantum Machine Learning Architectures

Michael Kölle, Jonas Maurer, Philipp J. Altmann, Leo Sünkel, Jonas Stein, Claudia Linnhoff–Popien

Published Jan 1, 2024• 7 citations
arXivHTMLPDF

Abstract

Quantum computing offers the potential for superior computational capabilities, particularly for data-intensive tasks. However, the current state of quantum hardware puts heavy restrictions on input size. To address this, hybrid transfer learning solutions have been developed, merging pre-trained classical models, capable of handling extensive inputs, with variational quantum circuits. Yet, it remains unclear how much each component -- classical and quantum -- contributes to the model's results. We propose a novel hybrid architecture: instead of utilizing a pre-trained network for compression, we employ an autoencoder to derive a compressed version of the input data. This compressed data is then channeled through the encoder part of the autoencoder to the quantum component. We assess our model's classification capabilities against two state-of-the-art hybrid transfer learning architectures, two purely classical architectures and one quantum architecture. Their accuracy is compared across four datasets: Banknote Authentication, Breast Cancer Wisconsin, MNIST digits, and AudioMNIST. Our research suggests that classical components significantly influence classification in hybrid transfer learning, a contribution often mistakenly ascribed to the quantum element. The performance of our model aligns with that of a variational quantum circuit using amplitude embedding, positioning it as a feasible alternative.

DOI
10.5220/0012381600003636

Related papers

Quantum Transfer Learning for MNIST Classification Using a Hybrid Quantum-Classical Approach

Soumyadip Sarkar

We implement a hybrid quantum-classical model for image classification that compresses MNIST digit images into a low-dimensional feature space and then maps these features onto a 5-qubit quantum state. First, an autoencoder compresses each $28\times28$ image (784 pixels) into a 64-dimensional latent vector, preserving salient features of the digit with minimal reconstruction error. We further reduce the latent representation to 5 principal components using Principal Component Analysis (PCA), to match the 5 available qubits. These 5 features are encoded as rotation angles in a quantum circuit with 5 qubits. The quantum feature map applies single-qubit rotations ($R_y$ gates) proportional to the feature values, followed by a Hadamard gate and a cascade of entangling CNOT gates to produce a non-product entangled state. Measuring the 5-qubit state yields a 32-dimensional probability distribution over basis outcomes, which serves as a quantum-enhanced feature vector for classification. A classical neural network with a softmax output is then trained on these 32-dimensional quantum feature vectors to predict the digit class. We evaluate the hybrid model on the MNIST dataset and compare it to a purely classical baseline that uses the 64-dimensional autoencoder latent features for classification. The results show that the hybrid model can successfully classify digits, demonstrating the feasibility of integrating quantum computing in the classification pipeline, although its accuracy (about 75\% on test data) currently falls below the classical baseline (about 98\% on the same compressed data).

arXiv:2408.03351•Aug 5, 2024•1 citation

Hybrid quantum-classical classifier based on tensor network and variational quantum circuit

Samuel Yen-Chi Chen, Chih-Min Huang, Chia-Wei Hsing +1 more

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.

arXiv:2011.14651•Nov 30, 2020•27 citations

Compress, Encode, Diagnose: PCA-Enhanced QNNs for Breast Cancer Classification

Aman Kumar Prajapati, Lupam K Saha, Mohammed Nabeel Ahsan +1 more

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 $\mathbf{5}$-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.

IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)•Nov 4, 2025•0 citations

Hybrid classical-quantum transfer learning for text classification

Ebrahim Ardeshir-Larijani, Mohammad Mahdi Nasiri Fatmehsari

Abstract Quantum Machine Learning (QML) is a promising field that combines the power of quantum computing with machine learning. Variational quantum circuits, where parameters of circuits are learned classically, have been widely used in many recent applications of QML. This is an instance of a hybrid quantum-classical framework, where both classical and quantum components are present. However, applying these techniques to applications involving massive data is a challenging task. One way to overcome this, is using the concept of classical-quantum transfer learning with the help of dressed quantum circuit, introduced recently, where the underlying neural architecture is pre-trained classically, but at the final steps (decision layer), a quantum circuit is used, followed by quantum measurements and post-processing to classify images with high precision. In this paper, we applied hybrid classical-quantum transfer learning to another task of massive data processing, i.e. Natural Language Processing (NLP). We show how to (binary) classify short texts (e.g., SMS) with classical-quantum transfer learning, which was originally applied to image processing only. Our quantum network was pre-trained by Bidirectional Encoder Representations from the Transformers (BERT) model, and its variational quantum circuit is fine-tuned for text processing. We evaluated the performance of our hybrid neural architecture using the Receiver Operating Characteristic (ROC) curve, which is typically used in the evaluation of classification problems. The results indicate high precision as well as lower loss function. To our knowledge, our work is the first application of quantum transfer learning to the area of NLP. Finally a comparison with a tool that uses learning but in a different way than transfer learning is presented

Quantum Machine Intelligence•Mar 17, 2024•23 citations

Bridging Classical and Quantum Machine Learning: Knowledge Transfer From Classical to Quantum Neural Networks Using Knowledge Distillation

Mohammad Junayed Hasan, M. R. C. Mahdy

Quantum neural networks (QNNs), harnessing superposition and entanglement, have shown potential to surpass classical methods in complex learning tasks but remain limited by hardware constraints and noisy conditions. In this work, we present a novel framework for transferring knowledge from classical convolutional neural networks (CNNs) to QNNs via knowledge distillation, thereby reducing the need for resource intensive quantum training and error mitigation. We conduct extensive experiments using two parameterized quantum circuits (PQCs) with 4 and 8 qubits on MNIST, Fashion MNIST, and CIFAR10 datasets. The approach demonstrates consistent accuracy improvements attributed to distilled knowledge from larger classical networks. Through ablation studies, we systematically compare the effect of state of the art dimensionality reduction techniques fully connected layers, center cropping, principal component analysis, and pooling to compress high-dimensional image data prior to quantum encoding. Our findings reveal that fully connected layers retain the most salient features for QNN inference, thereby surpassing other down sampling approaches. Additionally, we examine state of the art data encoding methods (amplitude, angle, and qubit encoding) and identify amplitude encoding as the optimal strategy, yielding superior accuracy across all tested datasets and qubit configurations. Through computational analyses, we show that our distilled 4-qubit and 8-qubit QNNs achieve competitive performance while utilizing significantly fewer parameters than their classical counterparts. Our results establish a promising paradigm for bridging classical deep learning and emerging quantum computing, paving the way for more powerful, resource conscious models in quantum machine intelligence.

arXiv:2311.13810•Nov 23, 2023•4 citations

Hybrid Quantum-Classical Transfer Learning for Parameter-Efficient Code Generation

Su-Chang Lim, Jong-Chan Kim

The remarkable success of large language models (LLMs) in code generation has transformed software development, with systems like Codex, CodeGen, and StarCoder demonstrating strong capabilities in synthesizing functional code from natural language descriptions. However, this progress comes at a steep computational cost. Modern code generation models require hundreds of millions to billions of parameters—GPT-3 contains 175 billion parameters, CodeGen-16B uses 16 billion, and the trend continues toward ever-larger models. This scale creates fundamental challenges in training cost, inference latency, memory consumption, and environmental impact. We present a quantum transfer learning framework as an alternative approach to classical model compression for code generation. By replacing selected MLP layers with variational quantum circuits (VQCs), we exploit the exponential representational capacity of quantum systems to achieve $\Theta (D \log D)$ parameter scaling instead of classical $\Theta (D^{2})$ . Our hybrid classical-quantum architecture balances three competing objectives: leveraging existing pre-trained knowledge, achieving parameter compression through quantum representation, and maintaining compatibility with near-term quantum hardware constraints. We demonstrate our approach on CodeGen-350M, a production-scale code generation model, adopting a bottleneck architecture that substantially reduces parameters compared to the original MLP layer. Through a fair comparison against a classical bottleneck baseline with near-identical parameter count, we show that the VQC achieves superior representational quality—lower perplexity and higher code generation accuracy—validating the quantum layer’s expressivity advantage in the compressed latent space. Our design employs data re-uploading, where classical input features are re-encoded at each variational layer via trainable RY gates, enhancing the circuit’s expressive power on near-term devices.

IEEE Access•Jan 1, 2026•0 citations
Quantum computing offers the potential for superior computational capabilities, particularly for data-intensive tasks. However, the current state of quantum hardware puts heavy restrictions on input size. To address this, hybrid transfer learning solutions have been developed, merging pre-trained classical models, capable of handling extensive inputs, with variational quantum circuits. Yet, it remains unclear how much each component -- classical and quantum -- contributes to the model's results. We propose a novel hybrid architecture: instead of utilizing a pre-trained network for compression, we employ an autoencoder to derive a compressed version of the input data. This compressed data is then channeled through the encoder part of the autoencoder to the quantum component. We assess our model's classification capabilities against two state-of-the-art hybrid transfer learning architectures, two purely classical architectures and one quantum architecture. Their accuracy is compared across four datasets: Banknote Authentication, Breast Cancer Wisconsin, MNIST digits, and AudioMNIST. Our research suggests that classical components significantly influence classification in hybrid transfer learning, a contribution often mistakenly ascribed to the quantum element. The performance of our model aligns with that of a variational quantum circuit using amplitude embedding, positioning it as a feasible alternative.
We implement a hybrid quantum-classical model for image classification that compresses MNIST digit images into a low-dimensional feature space and then maps these features onto a 5-qubit quantum state. First, an autoencoder compresses each 28×2828\times2828×28 image (784 pixels) into a 64-dimensional latent vector, preserving salient features of the digit with minimal reconstruction error. We further reduce the latent representation to 5 principal components using Principal Component Analysis (PCA), to match the 5 available qubits. These 5 features are encoded as rotation angles in a quantum circuit with 5 qubits. The quantum feature map applies single-qubit rotations (RyR_yRy​ gates) proportional to the feature values, followed by a Hadamard gate and a cascade of entangling CNOT gates to produce a non-product entangled state. Measuring the 5-qubit state yields a 32-dimensional probability distribution over basis outcomes, which serves as a quantum-enhanced feature vector for classification. A classical neural network with a softmax output is then trained on these 32-dimensional quantum feature vectors to predict the digit class. We evaluate the hybrid model on the MNIST dataset and compare it to a purely classical baseline that uses the 64-dimensional autoencoder latent features for classification. The results show that the hybrid model can successfully classify digits, demonstrating the feasibility of integrating quantum computing in the classification pipeline, although its accuracy (about 75\% on test data) currently falls below the classical baseline (about 98\% on the same compressed data).
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.
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\mathbf{5}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.
Abstract Quantum Machine Learning (QML) is a promising field that combines the power of quantum computing with machine learning. Variational quantum circuits, where parameters of circuits are learned classically, have been widely used in many recent applications of QML. This is an instance of a hybrid quantum-classical framework, where both classical and quantum components are present. However, applying these techniques to applications involving massive data is a challenging task. One way to overcome this, is using the concept of classical-quantum transfer learning with the help of dressed quantum circuit, introduced recently, where the underlying neural architecture is pre-trained classically, but at the final steps (decision layer), a quantum circuit is used, followed by quantum measurements and post-processing to classify images with high precision. In this paper, we applied hybrid classical-quantum transfer learning to another task of massive data processing, i.e. Natural Language Processing (NLP). We show how to (binary) classify short texts (e.g., SMS) with classical-quantum transfer learning, which was originally applied to image processing only. Our quantum network was pre-trained by Bidirectional Encoder Representations from the Transformers (BERT) model, and its variational quantum circuit is fine-tuned for text processing. We evaluated the performance of our hybrid neural architecture using the Receiver Operating Characteristic (ROC) curve, which is typically used in the evaluation of classification problems. The results indicate high precision as well as lower loss function. To our knowledge, our work is the first application of quantum transfer learning to the area of NLP. Finally a comparison with a tool that uses learning but in a different way than transfer learning is presented
Quantum neural networks (QNNs), harnessing superposition and entanglement, have shown potential to surpass classical methods in complex learning tasks but remain limited by hardware constraints and noisy conditions. In this work, we present a novel framework for transferring knowledge from classical convolutional neural networks (CNNs) to QNNs via knowledge distillation, thereby reducing the need for resource intensive quantum training and error mitigation. We conduct extensive experiments using two parameterized quantum circuits (PQCs) with 4 and 8 qubits on MNIST, Fashion MNIST, and CIFAR10 datasets. The approach demonstrates consistent accuracy improvements attributed to distilled knowledge from larger classical networks. Through ablation studies, we systematically compare the effect of state of the art dimensionality reduction techniques fully connected layers, center cropping, principal component analysis, and pooling to compress high-dimensional image data prior to quantum encoding. Our findings reveal that fully connected layers retain the most salient features for QNN inference, thereby surpassing other down sampling approaches. Additionally, we examine state of the art data encoding methods (amplitude, angle, and qubit encoding) and identify amplitude encoding as the optimal strategy, yielding superior accuracy across all tested datasets and qubit configurations. Through computational analyses, we show that our distilled 4-qubit and 8-qubit QNNs achieve competitive performance while utilizing significantly fewer parameters than their classical counterparts. Our results establish a promising paradigm for bridging classical deep learning and emerging quantum computing, paving the way for more powerful, resource conscious models in quantum machine intelligence.
The remarkable success of large language models (LLMs) in code generation has transformed software development, with systems like Codex, CodeGen, and StarCoder demonstrating strong capabilities in synthesizing functional code from natural language descriptions. However, this progress comes at a steep computational cost. Modern code generation models require hundreds of millions to billions of parameters—GPT-3 contains 175 billion parameters, CodeGen-16B uses 16 billion, and the trend continues toward ever-larger models. This scale creates fundamental challenges in training cost, inference latency, memory consumption, and environmental impact. We present a quantum transfer learning framework as an alternative approach to classical model compression for code generation. By replacing selected MLP layers with variational quantum circuits (VQCs), we exploit the exponential representational capacity of quantum systems to achieve Θ(Dlog⁡D)\Theta (D \log D)Θ(DlogD) parameter scaling instead of classical Θ(D2)\Theta (D^{2})Θ(D2) . Our hybrid classical-quantum architecture balances three competing objectives: leveraging existing pre-trained knowledge, achieving parameter compression through quantum representation, and maintaining compatibility with near-term quantum hardware constraints. We demonstrate our approach on CodeGen-350M, a production-scale code generation model, adopting a bottleneck architecture that substantially reduces parameters compared to the original MLP layer. Through a fair comparison against a classical bottleneck baseline with near-identical parameter count, we show that the VQC achieves superior representational quality—lower perplexity and higher code generation accuracy—validating the quantum layer’s expressivity advantage in the compressed latent space. Our design employs data re-uploading, where classical input features are re-encoded at each variational layer via trainable RY gates, enhancing the circuit’s expressive power on near-term devices.