Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Junghoon Justin Park, Yeonghyeon Park, Jiook Cha

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.

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

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 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.

Paper Structure

This paper contains 30 sections, 6 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Quantum Transfer Learning
  4. DIVER-1
  5. Quantum Time-series Transformer
  6. Unitary Temporal Embedding
  7. Time Sequence Mixing via LCU
  8. Non-linearity via QSVT
  9. Readout and Classical Processing
  10. Differentiable Quantum Architecture Search
  11. Search Space Construction
  12. Differentiable Optimization Framework
  13. Training and Discretization
  14. Q-DIVER
  15. Q-DIVER Hybrid Architecture
  16. ...and 15 more sections

Figures (2)

  • Figure 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).
  • Figure 2: Optimal Quantum Circuit Architecture Obtained from DiffQAS.