# R-Drop: Regularized Dropout for Neural Networks

arXiv: https://arxiv.org/abs/2106.14448 · HTML: https://mlsanity.com/paper/2106.14448/

## Key facts

- Cited by 202 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 101 references that are in the map.
- First posted on arXiv 28 Jun 2021.

## Builds on (most cited first, 30 of 63)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)

## Built on by (most cited first, 30 of 202)

- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition](https://mlsanity.com/paper/2310.05492/) (2023)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond](https://mlsanity.com/paper/2204.09269/) (2022)
- [UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units](https://mlsanity.com/paper/2212.08055/) (2022)
- [Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding](https://mlsanity.com/paper/2203.01515/) (2022)
- [On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation](https://mlsanity.com/paper/2205.03835/) (2022)
- [ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval](https://mlsanity.com/paper/2205.09153/) (2022)
- [SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding](https://mlsanity.com/paper/2204.10050/) (2022)
- [RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training](https://mlsanity.com/paper/2303.00534/) (2023)
- [Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment](https://mlsanity.com/paper/2405.17931/) (2024)
- [From Shortcuts to Triggers: Backdoor Defense with Denoised PoE](https://mlsanity.com/paper/2305.14910/) (2023)
- [HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2203.07376/) (2022)
- [Speech-to-Speech Translation For A Real-world Unwritten Language](https://mlsanity.com/paper/2211.06474/) (2022)
- [Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers](https://mlsanity.com/paper/2205.14336/) (2022)
- [DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization](https://mlsanity.com/paper/2308.10285/) (2023)
- [UnifieR: A Unified Retriever for Large-Scale Retrieval](https://mlsanity.com/paper/2205.11194/) (2022)
- [Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively](https://mlsanity.com/paper/2211.01642/) (2022)
- [CoRelation: Boosting Automatic ICD Coding Through Contextualized Code Relation Learning](https://mlsanity.com/paper/2402.15700/) (2024)
- [LoRA Meets Dropout under a Unified Framework](https://mlsanity.com/paper/2403.00812/) (2024)
- [CR-CTC: Consistency regularization on CTC for improved speech recognition](https://mlsanity.com/paper/2410.05101/) (2024)
- [Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives](https://mlsanity.com/paper/2206.02457/) (2022)
- [ZLPR: A Novel Loss for Multi-label Classification](https://mlsanity.com/paper/2208.02955/) (2022)
- [Are AI-Generated Text Detectors Robust to Adversarial Perturbations?](https://mlsanity.com/paper/2406.01179/) (2024)
- [RecursiveMix: Mixed Learning with History](https://mlsanity.com/paper/2203.06844/) (2022)
- [Understanding and Bridging the Modality Gap for Speech Translation](https://mlsanity.com/paper/2305.08706/) (2023)
- [Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards](https://mlsanity.com/paper/2210.12050/) (2022)
- [PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization](https://mlsanity.com/paper/2409.17137/) (2024)

## Abstract (arXiv)

Dropout is a powerful and widely used technique to regularize the training of deep neural networks. In this paper, we introduce a simple regularization strategy upon dropout in model training, namely R-Drop, which forces the output distributions of different sub models generated by dropout to be consistent with each other. Specifically, for each training sample, R-Drop minimizes the bidirectional KL-divergence between the output distributions of two sub models sampled by dropout. Theoretical analysis reveals that R-Drop reduces the freedom of the model parameters and complements dropout. Experiments on bf5 widely used deep learning tasks (bf18 datasets in total), including neural machine translation, abstractive summarization, language understanding, language modeling, and image classification, show that R-Drop is universally effective. In particular, it yields substantial improvements when applied to fine-tune large-scale pre-trained models, e.g., ViT, RoBERTa-large, and BART, and achieves state-of-the-art (SOTA) performances with the vanilla Transformer model on WMT14 English→German translation (bf30.91 BLEU) and WMT14 English→French translation (bf43.95 BLEU), even surpassing models trained with extra large-scale data and expert-designed advanced variants of Transformer models. Our code is available at GitHuburlhttps://github.com/dropreg/R-Drop.