IEEE Trans Pattern Anal Mach Intell. 2022 Sep;44(9):4555-4576. doi: 10.1109/TPAMI.2021.3069908. Epub 2022 Aug 4.
Curriculum learning (CL) is a training strategy that trains a machine learning model from easier data to harder data, which imitates the meaningful learning order in human curricula. As an easy-to-use plug-in, the CL strategy has demonstrated its power in improving the generalization capacity and convergence rate of various models in a wide range of scenarios such as computer vision and natural language processing etc. In this survey article, we comprehensively review CL from various aspects including motivations, definitions, theories, and applications. We discuss works on curriculum learning within a general CL framework, elaborating on how to design a manually predefined curriculum or an automatic curriculum. In particular, we summarize existing CL designs based on the general framework of Difficulty Measurer + Training Scheduler and further categorize the methodologies for automatic CL into four groups, i.e., Self-paced Learning, Transfer Teacher, RL Teacher, and Other Automatic CL. We also analyze principles to select different CL designs that may benefit practical applications. Finally, we present our insights on the relationships connecting CL and other machine learning concepts including transfer learning, meta-learning, continual learning and active learning, etc., then point out challenges in CL as well as potential future research directions deserving further investigations.
课程学习（CL）是一种从简单数据到困难数据的训练策略，它模仿了人类课程中的有意义的学习顺序。作为一种易于使用的插件，CL 策略在计算机视觉和自然语言处理等各种场景下提高了各种模型的泛化能力和收敛速度，展示了其强大的功能。在这篇综述文章中，我们从动机、定义、理论和应用等各个方面全面回顾了 CL。我们讨论了在一般 CL 框架内的课程学习工作，详细阐述了如何设计手动预定义的课程或自动课程。特别是，我们根据难度度量器+训练调度器的通用框架总结了现有的 CL 设计，并进一步将自动 CL 的方法分为四类，即自定步学习、转移教师、RL 教师和其他自动 CL。我们还分析了选择不同 CL 设计的原则，这些设计可能有益于实际应用。最后，我们提出了我们对 CL 与其他机器学习概念（包括迁移学习、元学习、持续学习和主动学习等）之间关系的见解，然后指出了 CL 中的挑战以及值得进一步研究的潜在未来研究方向。
