A Survey on Curriculum Learning

By Xin Wang, Yudong Chen, Wenwu Zhu. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021

1,000 citations recorded by the source corpus.

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 <italic>Difficulty Measurer <inline-formula><tex-math notation="LaTeX">$+$</tex-math><alternatives><mml:math><mml:mo>+</mml:mo></mml:math><inline-graphic xlink:href="wang-ieq1-3069908.gif"/></alternatives></inline-formula> Training Scheduler</italic> 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.

Subfields: Artificial Intelligence, Computer Science Applications

View Paper: https://www.semanticscholar.org/paper/55635aac4cd439a00356f83dad52bd8d7b0ea87e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Science Applications

Xiao-Dan Zhu

Citations in the corpus

MotionBERT: A Unified Perspective on Learning Human Motion Representations (2022, methodology): “We first train on 3D data only for 30 epochs, then train on both 3D data and 2D data for 60 epochs, following the curriculum learning practices [9, 118].”
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking (2021, background): “This paradigm is called curriculum learning (CL) (Bengio et al., 2009) and has been shown useful in various other problems (Wang et al., 2021).”
Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey (2025, neutral): “Curriculum Learning : Structure tasks in increasing order of complexity so that an agent develops basic skills that can be built upon in new, more complex tasks [26].”
Human-in-the-loop machine learning: a state of the art (2022, background): “Wang et al. (2021) present as an interesting idea for future research to embed human prior on sample importance into the fully data-driven CL meth-ods which has been explored in Wang et al. (2020).”