mlsanityData to 14 Oct 2026

Survey of Dropout Methods for Deep Neural Networks

arXiv 1904.13310 ↗First posted 25 Apr 2019cs.NE cs.AI cs.LGcited by 44

Not on the map. Why?

Abstract (arXiv)

Dropout methods are a family of stochastic techniques used in neural network training or inference that have generated significant research interest and are widely used in practice. They have been successfully applied in neural network regularization, model compression, and in measuring the uncertainty of neural network outputs. While original formulated for dense neural network layers, recent advances have made dropout methods also applicable to convolutional and recurrent neural network layers. This paper summarizes the history of dropout methods, their various applications, and current areas of research interest. Important proposed methods are described in additional detail.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 10; 2023: 10; 2024: 4; 2025: 9; 2026: 2.

44 papers.

Sort:

By area:

  1. 2021R-Drop: Regularized Dropout for Neural Networkscited by 202
  2. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  3. 2024Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitatecited by 47
  4. 2023Deep networks for system identification: a Surveycited by 37
  5. 2021EventDrop: data augmentation for event-based learningcited by 28
  6. 2023Dropout Reduces Underfittingcited by 21
  7. 2024Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimationcited by 18
  8. 2021On the Convergence of Shallow Neural Network Training with Randomly Masked Neuronscited by 11
  9. 2022Learning Robust Real-Time Cultural Transmission without Human Datacited by 9
  10. 2025Hadamard product in deep learning: Introduction, Advances and Challengescited by 9
  11. 2021Combining data assimilation and machine learning to estimate parameters of a convective-scale modelcited by 4
  12. 2022A Survey on Dropout Methods and Experimental Verification in Recommendationcited by 4
32 more
  1. 2023Training neural networks with structured noise improves classification and generalizationcited by 4
  2. 2025Dynamic DropConnect: Enhancing Neural Network Robustness through Adaptive Edge Dropping Strategiescited by 4
  3. 2021The challenge of reproducible ML: an empirical study on the impact of bugscited by 3
  4. 2022AA-Forecast: Anomaly-Aware Forecast for Extreme Eventscited by 3
  5. 2023Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modelingcited by 3
  6. 2022Information Geometry of Dropout Trainingcited by 2
  7. 2023Model-based feature selection for neural networks: A mixed-integer programming approachcited by 2
  8. 2023Robust Brain MRI Image Classification with SIBOW-SVMcited by 2
  9. 2025Regularization can make diffusion models more efficientcited by 2
  10. 2025Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmissioncited by 2
  11. 2025Deep Neural Networks Inspired by Differential Equationscited by 2
  12. 2021HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimizationcited by 1
  13. 2022Jalisco's multiclass land cover analysis and classification using a novel lightweight convnet with real-world multispectral and relief datacited by 1
  14. 2023Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understandingcited by 1
  15. 2023Deep Augmentation: Dropout as Augmentation for Self-Supervised Learningcited by 1
  16. 2024Enhancing Split Computing and Early Exit Applications through Predefined Sparsitycited by 1
  17. 2025Deep Learning on Hester Davis Scores for Inpatient Fall Predictioncited by 1
  18. 2026Robust Face Super-Resolution and Recognition Through Multi-Feature Aggregation in Diffusion Modelscited by 1
  19. 2021Redatuming physical systems using symmetric autoencoderscited by 0
  20. 2021Locally Learned Synaptic Dropout for Complete Bayesian Inferencecited by 0
  21. 2021Neural Networks for Infectious Diseases Detection: Prospects and Challengescited by 0
  22. 2022Weight Matrix Dimensionality Reduction in Deep Learning via Kronecker Multi-layer Architecturescited by 0
  23. 2022Dropout Inference with Non-Uniform Weight Scalingcited by 0
  24. 2022Adaptive Synaptic Failure Enables Sampling from Posterior Predictive Distributions in the Braincited by 0
  25. 2022Multilayer Perceptron Network Discriminates Larval Zebrafish Genotype using Behaviourcited by 0
  26. 2023Revisiting Implicit Models: Sparsity Trade-offs Capability in Weight-tied Model for Vision Taskscited by 0
  27. 2023Defensive Perception: Estimation and Monitoring of Neural Network Performance under Deploymentcited by 0
  28. 2024Demolition and Reinforcement of Memories in Spin-Glass-like Neural Networkscited by 0
  29. 2025Multitask LSTM for Arboviral Outbreak Prediction Using Public Health Datacited by 0
  30. 2025FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoEcited by 0
  31. 2025Improving action classification with brain-inspired deep networkscited by 0
  32. 2026Graph Neural Network with One-side Edge Sampling for Fraud Detectioncited by 0