用量子扩散模型提升少样本学习性能
Quantum Diffusion Models for Few-Shot Learning
- 设计三种基于量子扩散的少样本推理框架
- 在少样本任务上显著优于现有方法
- 适合对量子机器学习感兴趣的研究者
现代量子机器学习方法通常通过变分优化参数化量子线路在训练数据集上的表现，再在测试数据集上进行预测。然而，当前最先进的量子机器学习算法因学习能力有限，在少样本学习任务中缺乏实际优势。本文提出三种新框架，利用量子扩散模型（QDM）解决少样本学习问题：标签引导生成推理（LGGI）、标签引导去噪推理（LGDI）和标签引导加噪推理（LGNAI）。实验结果表明，所提出的算法显著优于现有方法。
原文摘要 · Abstract (English)
Modern quantum machine learning (QML) methods involve the variational optimization of parameterized quantum circuits on training datasets, followed by predictions on testing datasets. Most state-of-the-art QML algorithms currently lack practical advantages due to their limited learning capabilities, especially in few-shot learning tasks. In this work, we propose three new frameworks employing quantum diffusion model (QDM) as a solution for the few-shot learning: label-guided generation inference (LGGI); label-guided denoising inference (LGDI); and label-guided noise addition inference (LGNAI). Experimental results demonstrate that our proposed algorithms significantly outperform existing methods.
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。