# AutoDropout: Learning Dropout Patterns to Regularize Deep Networks

arXiv: https://arxiv.org/abs/2101.01761 · HTML: https://mlsanity.com/paper/2101.01761/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 72 references that are in the map.
- First posted on arXiv 5 Jan 2021.

## Builds on (most cited first, 30 of 61)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)

## Built on by (most cited first, 30 of 35)

- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- [CARD: Classification and Regression Diffusion Models](https://mlsanity.com/paper/2206.07275/) (2022)
- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization](https://mlsanity.com/paper/2106.00149/) (2021)
- [GFlowOut: Dropout with Generative Flow Networks](https://mlsanity.com/paper/2210.12928/) (2022)
- [On the Over-Memorization During Natural, Robust and Catastrophic Overfitting](https://mlsanity.com/paper/2310.08847/) (2023)
- [AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks](https://mlsanity.com/paper/2103.14026/) (2021)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [RankNAS: Efficient Neural Architecture Search by Pairwise Ranking](https://mlsanity.com/paper/2109.07383/) (2021)
- [SpliceOut: A Simple and Efficient Audio Augmentation Method](https://mlsanity.com/paper/2110.00046/) (2021)
- [Perturbation of Deep Autoencoder Weights for Model Compression and Classification of Tabular Data](https://mlsanity.com/paper/2205.08358/) (2022)
- [Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillation](https://mlsanity.com/paper/2209.15560/) (2022)
- [How to Use Dropout Correctly on Residual Networks with Batch Normalization](https://mlsanity.com/paper/2302.06112/) (2023)
- [Advancing Spiking Neural Networks towards Multiscale Spatiotemporal Interaction Learning](https://mlsanity.com/paper/2405.13672/) (2024)
- [Weight Expansion: A New Perspective on Dropout and Generalization](https://mlsanity.com/paper/2201.09209/) (2022)
- [Not All Attention Is All You Need](https://mlsanity.com/paper/2104.04692/) (2021)
- [The Adaptive Arms Race: Redefining Robustness in AI Security](https://mlsanity.com/paper/2312.13435/) (2023)
- [Evolving Neural Selection with Adaptive Regularization](https://mlsanity.com/paper/2204.01662/) (2022)
- [A Survey on Dropout Methods and Experimental Verification in Recommendation](https://mlsanity.com/paper/2204.02027/) (2022)
- [AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning](https://mlsanity.com/paper/2210.05883/) (2022)
- [FocusedDropout for Convolutional Neural Network](https://mlsanity.com/paper/2103.15425/) (2021)
- [Jitter: Random Jittering Loss Function](https://mlsanity.com/paper/2106.13749/) (2021)
- [On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications](https://mlsanity.com/paper/2111.09838/) (2021)
- [The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach](https://mlsanity.com/paper/2409.17370/) (2024)
- [Partial Graph Reasoning for Neural Network Regularization](https://mlsanity.com/paper/2106.01805/) (2021)
- [Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reduction](https://mlsanity.com/paper/2206.00913/) (2022)
- [ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision](https://mlsanity.com/paper/2304.09369/) (2023)
- [Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions](https://mlsanity.com/paper/2103.15383/) (2021)
- [Spiral Language Modeling](https://mlsanity.com/paper/2112.10543/) (2021)
- [Feature Weaken: Vicinal Data Augmentation for Classification](https://mlsanity.com/paper/2211.10944/) (2022)

## Abstract (arXiv)

Neural networks are often over-parameterized and hence benefit from aggressive regularization. Conventional regularization methods, such as Dropout or weight decay, do not leverage the structures of the network's inputs and hidden states. As a result, these conventional methods are less effective than methods that leverage the structures, such as SpatialDropout and DropBlock, which randomly drop the values at certain contiguous areas in the hidden states and setting them to zero. Although the locations of dropout areas random, the patterns of SpatialDropout and DropBlock are manually designed and fixed. Here we propose to learn the dropout patterns. In our method, a controller learns to generate a dropout pattern at every channel and layer of a target network, such as a ConvNet or a Transformer. The target network is then trained with the dropout pattern, and its resulting validation performance is used as a signal for the controller to learn from. We show that this method works well for both image recognition on CIFAR-10 and ImageNet, as well as language modeling on Penn Treebank and WikiText-2. The learned dropout patterns also transfers to different tasks and datasets, such as from language model on Penn Treebank to Engligh-French translation on WMT 2014. Our code will be available.