# A Survey on Curriculum Learning

arXiv: https://arxiv.org/abs/2010.13166 · HTML: https://mlsanity.com/paper/2010.13166/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2020.

## Built on by (most cited first, 15 of 15)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-based Convolutional Neural Networks](https://mlsanity.com/paper/2109.10742/) (2021)
- [Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning](https://mlsanity.com/paper/2104.10461/) (2021)
- [TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding](https://mlsanity.com/paper/2506.21393/) (2025)
- [Interpretable Low-Resource Legal Decision Making](https://mlsanity.com/paper/2201.01164/) (2022)
- [Confidence-Guided Learning Process for Continuous Classification of Time Series](https://mlsanity.com/paper/2208.06883/) (2022)
- [LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching](https://mlsanity.com/paper/2108.02915/) (2021)
- [Multi-Task Learning based Convolutional Models with Curriculum Learning for the Anisotropic Reynolds Stress Tensor in Turbulent Duct Flow](https://mlsanity.com/paper/2111.00328/) (2021)
- [Linking-Enhanced Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2111.09486/) (2021)
- [Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training](https://mlsanity.com/paper/2208.07075/) (2022)
- [Constraint-driven multi-task learning](https://mlsanity.com/paper/2208.11656/) (2022)
- [RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses](https://mlsanity.com/paper/2604.28056/) (2026)
- [Towards Scheduling Federated Deep Learning using Meta-Gradients for Inter-Hospital Learning](https://mlsanity.com/paper/2107.01707/) (2021)
- [Pre-trained Language Models as Re-Annotators](https://mlsanity.com/paper/2205.05368/) (2022)
- [FOSSIL: Regret-Minimizing Curriculum Learning for Metadata-Free and Low-Data Mpox Diagnosis](https://mlsanity.com/paper/2510.10041/) (2025)

## Abstract (arXiv)

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.