mlsanityData to 7 Oct 2026

Data Distribution-based Curriculum Learning

arXiv 2402.07352 ↗First posted 12 Feb 2024cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

The order of training samples can have a significant impact on the performance of a classifier. Curriculum learning is a method of ordering training samples from easy to hard. This paper proposes the novel idea of a curriculum learning approach called Data Distribution-based Curriculum Learning (DDCL). DDCL uses the data distribution of a dataset to build a curriculum based on the order of samples. Two types of scoring methods known as DDCL (Density) and DDCL (Point) are used to score training samples thus determining their training order. DDCL (Density) uses the sample density to assign scores while DDCL (Point) utilises the Euclidean distance for scoring. We evaluate the proposed DDCL approach by conducting experiments on multiple datasets using a neural network, support vector machine and random forest classifier. Evaluation results show that the application of DDCL improves the average classification accuracy for all datasets compared to standard evaluation without any curriculum. Moreover, analysis of the error losses for a single training epoch reveals that convergence is faster when using DDCL over the no curriculum method.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 47 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

20 of 47 references.

References · 20

  1. 2016An overview of gradient descent optimization algorithmscited by 1,021
  2. 2016Learning to learn by gradient descent by gradient descentcited by 616
  3. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  4. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  5. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  6. 2021Curriculum Learning: A Surveycited by 257
  7. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  8. 2018Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networkscited by 113
  9. 2019Dynamic Curriculum Learning for Imbalanced Data Classificationcited by 93
  10. 2018Hyperparameters and Tuning Strategies for Random Forestcited by 83
  11. 2022Competence-based Multimodal Curriculum Learning for Medical Report Generationcited by 74
  12. 2019Pseudo-Labeling Curriculum for Unsupervised Domain Adaptationcited by 46
8 more
  1. 2018Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Datacited by 25
  2. 2021SMOTified-GAN for class imbalanced pattern classification problemscited by 20
  3. 2015Structured Training for Neural Network Transition-Based Parsingcited by 11
  4. 2020Guided Curriculum Learning for Walking Over Complex Terraincited by 10
  5. 2017Curriculum Learning of Visual Attribute Clusters for Multi-Task Classificationcited by 8
  6. 2020How to tune the RBF SVM hyperparameters?: An empirical evaluation of 18 search algorithmscited by 7
  7. 2023From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learningcited by 6
  8. 2021Guided parallelized stochastic gradient descent for delay compensationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Mid-Training of Large Language Models: A Surveycited by 18
  2. 2026Dual-Criterion Curriculum Learning: Application to Temporal Datacited by 0