# X-SHIELD: Regularization for eXplainable Artificial Intelligence

arXiv: https://arxiv.org/abs/2404.02611 · HTML: https://mlsanity.com/paper/2404.02611/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 3 Apr 2024.

## Builds on (most cited first, 24 of 24)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [Sanity Checks for Saliency Metrics](https://mlsanity.com/paper/1912.01451/) (2019)
- [Improving Deep Learning Interpretability by Saliency Guided Training](https://mlsanity.com/paper/2111.14338/) (2021)
- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods](https://mlsanity.com/paper/2106.00461/) (2021)
- [Implicit regularization of dropout](https://mlsanity.com/paper/2207.05952/) (2022)
- [Position: Explain to Question not to Justify](https://mlsanity.com/paper/2402.13914/) (2024)
- [Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets](https://mlsanity.com/paper/2311.01961/) (2023)
- [Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data](https://mlsanity.com/paper/1910.07856/) (2019)
- [REVEL Framework to measure Local Linear Explanations for black-box models: Deep Learning Image Classification case of study](https://mlsanity.com/paper/2211.06154/) (2022)

## Built on by (most cited first, 3 of 3)

- [Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundational Models](https://mlsanity.com/paper/2408.01431/) (2024)
- [SHAP-Guided Regularization in Machine Learning Models](https://mlsanity.com/paper/2507.23665/) (2025)
- [Explaining f-Divergence-Based Regularization via Local Curvature and Sharpness-Aware Minimization](https://mlsanity.com/paper/2609.09367/) (2026)

## Abstract (arXiv)

As artificial intelligence systems become integral across domains, the demand for explainability grows, the called eXplainable artificial intelligence (XAI). Existing efforts primarily focus on generating and evaluating explanations for black-box models while a critical gap in directly enhancing models remains through these evaluations. It is important to consider the potential of this explanation process to improve model quality with a feedback on training as well. XAI may be used to improve model performance while boosting its explainability. Under this view, this paper introduces Transformation - Selective Hidden Input Evaluation for Learning Dynamics (T-SHIELD), a regularization family designed to improve model quality by hiding features of input, forcing the model to generalize without those features. Within this family, we propose the XAI - SHIELD(X-SHIELD), a regularization for explainable artificial intelligence, which uses explanations to select specific features to hide. In contrast to conventional approaches, X-SHIELD regularization seamlessly integrates into the objective function enhancing model explainability while also improving performance. Experimental validation on benchmark datasets underscores X-SHIELD's effectiveness in improving performance and overall explainability. The improvement is validated through experiments comparing models with and without the X-SHIELD regularization, with further analysis exploring the rationale behind its design choices. This establishes X-SHIELD regularization as a promising pathway for developing reliable artificial intelligence regularization.