Quantum machine learning (QML) requires significant quantum resources to achieve quantum advantage. Research should prioritize both the efficient design of quantum architectures and the development of learning strategies to optimize resource usage. We propose a framework called quantum curriculum learning (Q-CurL) for quantum data, where the curriculum introduces simpler tasks or data to the learning model before progressing to more challenging ones. We define the curriculum criteria based on the data density ratio between tasks to determine the curriculum order. We also implement a dynamic learning schedule to emphasize the significance of quantum data in optimizing the loss function. Empirical evidence shows that Q-CurL significantly enhances the training convergence and the generalization for unitary learning tasks and improves the robustness of quantum phase recognition tasks. Our framework provides a general learning strategy, bringing QML closer to realizing practical advantages.

翻译：量子机器学习（QML）需要大量量子资源以实现量子优势。研究应同时关注量子架构的高效设计以及优化资源使用的学习策略开发。我们提出了一种针对量子数据的框架，称为量子课程学习（Q-CurL），其中课程在学习模型处理更具挑战性的任务或数据之前，先引入更简单的任务或数据。我们基于任务间的数据密度比定义了课程标准，以确定课程顺序。我们还实现了一种动态学习调度机制，以强调量子数据在优化损失函数中的重要性。实证证据表明，Q-CurL显著提升了酉学习任务的训练收敛性和泛化能力，并增强了量子相识别任务的鲁棒性。我们的框架提供了一种通用的学习策略，使QML更接近实现实际优势。