# DenoGrad: A Gradient-Based Framework for Data Refinement in Tabular and Time-Series Learning

arXiv: https://arxiv.org/abs/2511.10161 · HTML: https://mlsanity.com/paper/2511.10161/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 58 references that are in the map.
- First posted on arXiv 13 Nov 2025.

## Builds on (most cited first, 29 of 29)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [xLSTM: Extended Long Short-Term Memory](https://mlsanity.com/paper/2405.04517/) (2024)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [Probabilistic End-to-end Noise Correction for Learning with Noisy Labels](https://mlsanity.com/paper/1903.07788/) (2019)
- [Generalized Sliced Wasserstein Distances](https://mlsanity.com/paper/1902.00434/) (2019)
- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [Meta Label Correction for Noisy Label Learning](https://mlsanity.com/paper/1911.03809/) (2019)
- [Explicit Regularisation in Gaussian Noise Injections](https://mlsanity.com/paper/2007.07368/) (2020)
- [Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning](https://mlsanity.com/paper/2409.06219/) (2024)
- [Enabling Smart Data: Noise filtering in Big Data classification](https://mlsanity.com/paper/1704.01770/) (2017)
- [Three-quarter Sibling Regression for Denoising Observational Data](https://mlsanity.com/paper/2101.00074/) (2020)
- [DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer](https://mlsanity.com/paper/2207.13861/) (2022)
- [Generative Models for Periodicity Detection in Noisy Signals](https://mlsanity.com/paper/2201.07896/) (2022)

## Abstract (arXiv)

In the Data-Centric Artificial Intelligence (AI) paradigm, improving data quality is essential for robust machine learning. However, many denoising methods rely on rigid statistical assumptions or require clean reference data, which limits their applicability in real-world scenarios. In this work, we propose DenoGrad, a gradient-based framework for data refinement that leverages a pretrained neural network to iteratively correct noisy observations by optimizing the input space while keeping the model fixed. DenoGrad is applicable to both tabular regression and time-series forecasting, and incorporates a consensus-based strategy to ensure temporally coherent updates in sequential settings. Experiments on ten real-world datasets show that the proposed approach yields consistent improvements in downstream predictive performance while preserving the statistical structure of the data, as measured by distributional and correlation-based metrics. In addition, DenoGrad can improve generalization in nominally clean datasets, acting as a form of dataset-level regularization. These results support model-guided data refinement as a practical component of data-centric machine learning workflows. Code is available at: https://github.com/ari-dasci/S-DenoGrad.