# A Unified Plug-and-Play Framework for Effective Data Denoising and Robust Abstention

arXiv: https://arxiv.org/abs/2009.12027 · HTML: https://mlsanity.com/paper/2009.12027/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 4 of 4)

- [Controlled abstention neural networks for identifying skillful predictions for regression problems](https://mlsanity.com/paper/2104.08236/) (2021)
- [Controlled abstention neural networks for identifying skillful predictions for classification problems](https://mlsanity.com/paper/2104.08281/) (2021)
- [Reducing Risk and Uncertainty of Deep Neural Networks on Diagnosing COVID-19 Infection](https://mlsanity.com/paper/2104.14029/) (2021)
- [Abstaining Machine Learning -- Philosophical Considerations](https://mlsanity.com/paper/2409.00706/) (2024)

## Abstract (arXiv)

The success of Deep Neural Networks (DNNs) highly depends on data quality. Moreover, predictive uncertainty makes high performing DNNs risky for real-world deployment. In this paper, we aim to address these two issues by proposing a unified filtering framework leveraging underlying data density, that can effectively denoise training data as well as avoid predicting uncertain test data points. Our proposed framework leverages underlying data distribution to differentiate between noise and clean data samples without requiring any modification to existing DNN architectures or loss functions. Extensive experiments on multiple image classification datasets and multiple CNN architectures demonstrate that our simple yet effective framework can outperform the state-of-the-art techniques in denoising training data and abstaining uncertain test data.