用量子模型实现高效脑电信号分类,参数量少50倍。
Q-DIVER: Integrated Quantum Transfer Learning and Differentiable Quantum Architecture Search with EEG Data
- 结合预训练脑电编码器与可微量子架构搜索,自动优化量子电路结构。
- 在脑电数据集上达到63.49%的测试F1值,参数仅210万(传统模型10502万)。
- 适合追求低参数高效率的生物信号处理研究者,尤其关注量子机器学习落地。
将量子电路集成到深度学习流程中仍面临设计依赖经验的问题。本文提出Q-DIVER,一个融合大规模预训练脑电编码器(DIVER-1)与可微量子分类器的混合框架。不同于固定结构方法,我们采用可微量子架构搜索,在端到端微调过程中自主发现任务最优电路拓扑。在PhysioNet运动想象数据集上,该量子分类器取得与经典多层感知机相当的预测性能(测试F1: 63.49%),同时仅需约50倍更少的任务特定头参数(210万 vs. 10502万)。结果验证了量子迁移学习作为高维生物信号处理中的参数高效策略的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。