mlsanityData to 7 Oct 2026

Automated Curriculum Learning for Neural Networks

arXiv 1704.03003 ↗First posted 10 Apr 2017cs.NEcited by 251

Not on the map. Why?

Abstract (arXiv)

We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency. A measure of the amount that the network learns from each data sample is provided as a reward signal to a nonstationary multi-armed bandit algorithm, which then determines a stochastic syllabus. We consider a range of signals derived from two distinct indicators of learning progress: rate of increase in prediction accuracy, and rate of increase in network complexity. Experimental results for LSTM networks on three curricula demonstrate that our approach can significantly accelerate learning, in some cases halving the time required to attain a satisfactory performance level.

Key facts. Cited by 251 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 43; 2022: 39; 2023: 40; 2024: 34; 2025: 39; 2026: 55.

251 papers.

Sort:

By area:

  1. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  2. 2021Curriculum Learning: A Surveycited by 257
  3. 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Promptscited by 189
  4. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  5. 2025Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoningcited by 89
  6. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
  7. 2023OMNI: Open-endedness via Models of human Notions of Interestingnesscited by 66
  8. 2022Do Current Multi-Task Optimization Methods in Deep Learning Even Help?cited by 60
  9. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  10. 2024Adaptive Data Optimization: Dynamic Sample Selection with Scaling Lawscited by 46
  11. 2025DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-trainingcited by 45
  12. 2025Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modelingcited by 44
38 more
  1. 2022Information-theoretic Online Memory Selection for Continual Learningcited by 42
  2. 2022EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbonescited by 42
  3. 2021Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skillscited by 39
  4. 2021Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraftcited by 34
  5. 2021PML: Progressive Margin Loss for Long-tailed Age Classificationcited by 32
  6. 2022Environment Generation for Zero-Shot Compositional Reinforcement Learningcited by 32
  7. 2023Curriculum Learning for ab initio Deep Learned Refractive Opticscited by 32
  8. 2023A Survey on Dataset Distillation: Approaches, Applications and Future Directionscited by 32
  9. 2022Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundariescited by 31
  10. 2024Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Modelscited by 31
  11. 2022The Effect of Task Ordering in Continual Learningcited by 30
  12. 2021Teaching Humans When To Defer to a Classifier via Exemplarscited by 29
  13. 2023A Review of Deep Learning for Video Captioningcited by 28
  14. 2023Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understandingcited by 28
  15. 2026PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competencecited by 26
  16. 2024Swift Sampler: Efficient Learning of Sampler by 10 Parameterscited by 25
  17. 2021Weighted Training for Cross-Task Learningcited by 22
  18. 2023Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputscited by 22
  19. 2021Representation Learning Beyond Linear Prediction Functionscited by 21
  20. 2022METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signalscited by 20
  21. 2022General Intelligence Requires Rethinking Explorationcited by 20
  22. 2024CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-trainingcited by 20
  23. 2025Learning to Reason at the Frontier of Learnabilitycited by 20
  24. 2021Solving Compositional Reinforcement Learning Problems via Task Reductioncited by 19
  25. 2023A Mathematical Model for Curriculum Learning for Paritiescited by 19
  26. 2023Proximal Curriculum for Reinforcement Learning Agentscited by 19
  27. 2021TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RLcited by 18
  28. 2021Curriculum Learning for Vision-and-Language Navigationcited by 18
  29. 2022GraB: Finding Provably Better Data Permutations than Random Reshufflingcited by 18
  30. 2023Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasetscited by 18
  31. 2024MallowsPO: Fine-Tune Your LLM with Preference Dispersionscited by 18
  32. 2021Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixingcited by 16
  33. 2021Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Banditscited by 16
  34. 2024EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Trainingcited by 16
  35. 2024A Short Survey on Importance Weighting for Machine Learningcited by 15
  36. 2021Accelerating Neural Architecture Search via Proxy Datacited by 14
  37. 2022Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localizationcited by 14
  38. 2022It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generationcited by 14

50 most cited of 251 All 251 (JSON)