DenoGrad: Deep Gradient Denoising Framework for Enhancing the Performance of Interpretable AI Models

2025-11-13

AI Summary

Explainable AI (XAI) models suffer performance degradation under noise in training and production data; existing denoising methods often distort the original data distribution, compromising the fidelity of data patterns essential for interpretability. To address this, we propose the first deep learning gradient-based instance-level denoising framework. Leveraging task-specific high-quality model gradients, it performs gradient inversion to detect and adaptively correct noise, dynamically refining noisy instances while strictly preserving the underlying data distribution. We introduce a novel task-adaptive noise definition mechanism, enabling effective application to both tabular and time-series data. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art approaches across diverse noise settings, simultaneously improving model accuracy, robustness, and interpretability—crucially maintaining strict fidelity to the true data distribution.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The performance of Machine Learning (ML) models, particularly those operating within the Interpretable Artificial Intelligence (Interpretable AI) framework, is significantly affected by the presence of noise in both training and production data. Denoising has therefore become a critical preprocessing step, typically categorized into instance removal and instance correction techniques. However, existing correction approaches often degrade performance or oversimplify the problem by altering the original data distribution. This leads to unrealistic scenarios and biased models, which is particularly problematic in contexts where interpretable AI models are employed, as their interpretability depends on the fidelity of the underlying data patterns. In this paper, we argue that defining noise independently of the solution may be ineffective, as its nature can vary significantly across tasks and datasets. Using a task-specific high quality solution as a reference can provide a more precise and adaptable noise definition. To this end, we propose DenoGrad, a novel Gradient-based instance Denoiser framework that leverages gradients from an accurate Deep Learning (DL) model trained on the target data -- regardless of the specific task -- to detect and adjust noisy samples. Unlike conventional approaches, DenoGrad dynamically corrects noisy instances, preserving problem's data distribution, and improving AI models robustness. DenoGrad is validated on both tabular and time series datasets under various noise settings against the state-of-the-art. DenoGrad outperforms existing denoising strategies, enhancing the performance of interpretable IA models while standing out as the only high quality approach that preserves the original data distribution.

Problem

• Noise in training data impairs interpretable AI model performance
• Existing correction methods distort data distribution causing model bias
• Task-independent noise definitions are ineffective across diverse datasets

Innovation

• DenoGrad uses gradients from deep learning models
• It dynamically corrects noisy instances without altering data
• This framework preserves original data distribution while denoising