# DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification

arXiv: https://arxiv.org/abs/2209.05297 · HTML: https://mlsanity.com/paper/2209.05297/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 12 Sep 2022.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [MixUp as Locally Linear Out-Of-Manifold Regularization](https://mlsanity.com/paper/1809.02499/) (2018)
- [Good-Enough Compositional Data Augmentation](https://mlsanity.com/paper/1904.09545/) (2019)
- [Improving the Robustness of Deep Neural Networks via Stability Training](https://mlsanity.com/paper/1604.04326/) (2016)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [Syntactic Data Augmentation Increases Robustness to Inference Heuristics](https://mlsanity.com/paper/2004.11999/) (2020)
- [Sequence-Level Mixed Sample Data Augmentation](https://mlsanity.com/paper/2011.09039/) (2020)
- [AdvAug: Robust Adversarial Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2006.11834/) (2020)
- [Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge](https://mlsanity.com/paper/1808.08609/) (2018)
- [SSMix: Saliency-Based Span Mixup for Text Classification](https://mlsanity.com/paper/2106.08062/) (2021)
- [MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks](https://mlsanity.com/paper/2103.06132/) (2021)
- [LINDA: Unsupervised Learning to Interpolate in Natural Language Processing](https://mlsanity.com/paper/2112.13969/) (2021)
- [A Data Cartography based MixUp for Pre-trained Language Models](https://mlsanity.com/paper/2205.03403/) (2022)

## Built on by (most cited first, 10 of 10)

- [A Comprehensive Survey on Data Augmentation](https://mlsanity.com/paper/2405.09591/) (2024)
- [Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification](https://mlsanity.com/paper/2408.16266/) (2024)
- [Enhancing In-Context Learning via Implicit Demonstration Augmentation](https://mlsanity.com/paper/2407.00100/) (2024)
- [SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training](https://mlsanity.com/paper/2210.12653/) (2022)
- [LM-mixup: Text Data Augmentation via Language Model based Mixup](https://mlsanity.com/paper/2510.20449/) (2025)
- [Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation](https://mlsanity.com/paper/2403.15512/) (2024)
- [MSMix:An Interpolation-Based Text Data Augmentation Method Manifold Swap Mixup](https://mlsanity.com/paper/2305.19617/) (2023)
- [Probabilistic Linguistic Knowledge and Token-level Text Augmentation](https://mlsanity.com/paper/2306.16644/) (2023)
- [Summarization-based Data Augmentation for Document Classification](https://mlsanity.com/paper/2312.00513/) (2023)
- [Evaluation Metrics for Text Data Augmentation in NLP](https://mlsanity.com/paper/2402.06766/) (2024)

## Abstract (arXiv)

This paper proposes a simple yet effective interpolation-based data augmentation approach termed DoubleMix, to improve the robustness of models in text classification. DoubleMix first leverages a couple of simple augmentation operations to generate several perturbed samples for each training data, and then uses the perturbed data and original data to carry out a two-step interpolation in the hidden space of neural models. Concretely, it first mixes up the perturbed data to a synthetic sample and then mixes up the original data and the synthetic perturbed data. DoubleMix enhances models' robustness by learning the "shifted" features in hidden space. On six text classification benchmark datasets, our approach outperforms several popular text augmentation methods including token-level, sentence-level, and hidden-level data augmentation techniques. Also, experiments in low-resource settings show our approach consistently improves models' performance when the training data is scarce. Extensive ablation studies and case studies confirm that each component of our approach contributes to the final performance and show that our approach exhibits superior performance on challenging counterexamples. Additionally, visual analysis shows that text features generated by our approach are highly interpretable. Our code for this paper can be found at https://github.com/declare-lab/DoubleMix.git.