用量子生成对抗网络增强量子-经典神经网络的数据，提升模型性能。
QGAN-based data augmentation for hybrid quantum-classical neural networks
- 将量子生成对抗网络融入混合量子-经典网络，实现数据增强。
- 在MNIST上表现优于传统方法，参数减半仍保持相近效果。
- 适合研究量子机器学习、模型压缩与高质量数据生成的学者。
量子神经网络收敛更快且准确率高于经典模型，但量子机器学习中的数据增强仍不充分。为应对数据稀缺问题，本文将量子生成对抗网络（QGAN）与混合量子-经典神经网络（HQCNN）结合，提出一种增强框架。设计两种策略：通用策略提升整体数据处理与分类能力；定制策略动态生成针对特定类别性能优化的样本，增强复杂数据的学习能力。在MNIST数据集上的仿真实验表明，QGAN优于传统数据增强方法和经典GAN。相比基线DCGAN，QGAN以一半参数量达到相当性能，兼顾效率与效果。结果表明，QGAN可简化模型并生成高质量数据，提升HQCNN的准确性与性能，为量子数据增强在机器学习中的应用铺平道路。
原文摘要 · Abstract (English)
Quantum neural networks converge faster and achieve higher accuracy than classical models. However, data augmentation in quantum machine learning remains underexplored. To tackle data scarcity, we integrate quantum generative adversarial networks (QGANs) with hybrid quantum-classical neural networks (HQCNNs) to develop an augmentation framework. We propose two strategies: a general approach to enhance data processing and classification across HQCNNs, and a customized strategy that dynamically generates samples tailored to the HQCNN's performance on specific data categories, improving its ability to learn from complex datasets. Simulation experiments on the MNIST dataset demonstrate that QGAN outperforms traditional data augmentation methods and classical GANs. Compared to baseline DCGAN, QGAN achieves comparable performance with half the parameters, balancing efficiency and effectiveness. This suggests that QGANs can simplify models and generate high-quality data, enhancing HQCNN accuracy and performance. These findings pave the way for applying quantum data augmentation techniques in machine learning.
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。