Q-DIVER: Integrated Quantum Transfer Learning and Differentiable Quantum Architecture Search with EEG Data

Junghoon Justin Park; Yeonghyeon Park; Jiook Cha

quant-phMar 30, 2026

Q-DIVER: Integrated Quantum Transfer Learning and Differentiable Quantum Architecture Search with EEG Data

Authors: Junghoon Justin Park, Yeonghyeon Park, Jiook Cha

Organizations: Seoul National University, Seoul, Korea

Abstract

Integrating quantum circuits into deep learning pipelines remains challenging due to heuristic design limitations. We propose Q-DIVER, a hybrid framework combining a large-scale pretrained EEG encoder (DIVER-1) with a differentiable quantum classifier. Unlike fixed-ansatz approaches, we employ Differentiable Quantum Architecture Search to autonomously discover task-optimal circuit topologies during end-to-end fine-tuning. On the PhysioNet Motor Imagery dataset, our quantum classifier achieves predictive performance comparable to classical multi-layer perceptrons (Test F1: 63.49%) while using approximately \textbf{50 $\times$ fewer task-specific head parameters} (2.10M vs. 105.02M). These results validate quantum transfer learning as a parameter-efficient strategy for high-dimensional biological signal processing.

Figures & tables

Fig. 1 : Overview of the Q-DIVER hybrid architecture. Raw EEG signals are processed by the pretrained DIVER-1 backbone and passed to a QTSTransformer-based quantum head. DiffQAS is applied to the Timestep and QFF circuit blocks (24 candidates each).

Component	DIVER+MLP	DIVER+QTSTransformer
DIVER-1 Backbone	51.36M	51.36M
Feature Projection	—	2.10M
Classifier	105.02M	143
Total	156.38M	53.46M

TABLE I : Parameter breakdown comparison between DIVER+MLP and DIVER+QTSTransformer (PhysioNet-MI, 4-second trial setting, 8 qubits). Both models are trained end-to-end.

Component	Options
Initialization	$\{\text{Hadamard},\text{None}\}$
Entanglement	$\{\text{Linear CNOT},\text{Ring CNOT}$ , $\text{CRX Forward},\text{CRX Backward}\}$
Variational Gates	$\{\text{RX},\text{RY},\text{RZ}\}$

TABLE II : Search Space for Differentiable Quantum Architecture Search

Split	Accuracy	F1-Score	Kappa	Precision	Recall
Validation	59.77%	59.81%	0.4636	59.89%	59.77%
Test	63.39%	63.49%	0.5118	63.91%	63.38%

TABLE III : Classification performance metrics for the Q-DIVER model on the PhysioNet-MI dataset

Panel of Figure 5 — Fig. 2 : Optimal Quantum Circuit Architecture Obtained from DiffQAS.

Quantum Machine Learning

Quantum machine learning uses quantum circuits and quantum data to build learning algorithms and study their computational and statistical limits.

See all 256 papers

Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits
Mar 17, 2026D. Martín-Pérez, F. Rodríguez-Díaz, D. Gutiérrez-Avilés +2Quantum Machine Learning Hybrid Quantum-Classical ML
Data Science and Big Data Lab, Pablo de Olavide University, Seville, Spain · Department of Computer Science, University of Seville, Seville, Spain
Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification
Aug 7, 2026Hao-Yuan ChenHybrid Quantum-Classical ML Variational Quantum Circuits
Computer Science, University of London
Evolving Hybrid Quantum-Classical Architectures for Image Classification
Oct 2, 2026Devroop Kar, Daniel Krutz, Travis DesellHybrid Quantum-Classical ML Quantum Architecture Search
Rochester Institute of Technology Rochester, NY 14623, USA

Mar 17, 2026J/K move · Enter open · S save

Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits

D. Martín-Pérez, F. Rodríguez-Díaz, D. Gutiérrez-Avilés, A. Troncoso+1

Data Science and Big Data Lab, Pablo de Olavide University, Seville, Spain · Department of Computer Science, University of Seville, Seville, Spain

Quantum Machine Learning Hybrid Quantum-Classical ML Image Classification Variational Quantum Circuits

Open paper AskPDF arXiv

Quantum transfer learning combines pretrained classical deep learning models with quantum circuits to reuse expressive feature representations while limiting the number of trainable parameters. In this work, we introduce a family of compact quantum transfer learning architectures that attach variational quantum classifiers to frozen convolutional backbones for image classification. We instantiate and evaluate several classical-quantum hybrid models implemented in PennyLane and Qiskit, and systematically compare them with a classical transfer-learning baseline across heterogeneous image datasets. To ensure a realistic assessment, we evaluate all approaches under both ideal simulation and noisy emulation using noise models calibrated from IBM quantum hardware specifications, as well as on real IBM quantum hardware. Experimental results show that the proposed quantum transfer learning architectures achieve competitive and, in several cases, superior accuracy while consistently reducing training time and energy consumption relative to the classical baseline. Among the evaluated approaches, PennyLane-based implementations provide the most favorable trade-off between accuracy and computational efficiency, suggesting that hybrid quantum transfer learning can offer practical benefits in realistic NISQ era settings when feature extraction remains classical.

Abstract

Quantum Machine Learning

Explore similar work

Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits

Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification

Evolving Hybrid Quantum-Classical Architectures for Image Classification