• Home
  • Search
  • X-SHIELD: Regularization for explainable Artificial Intelligence
  • https://doi.org/10.1007/s11633-025-1576-yCopy DOI Icon

X-SHIELD: Regularization for explainable Artificial Intelligence

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Similar Papers
Abstract

Abstract As artificial intelligence systems become integral across domains, the demand for explainability, called eXplainable artificial intelligence (XAI), grows. Existing efforts have focused primarily 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 feedback on training as well. XAI may be used to improve model performance while increasing model 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 XAI-SHIELD (X-SHIELD), a regularization for explainable artificial intelligence that 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 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.

Loading PDF

Similar Papers
  • Research Article
  • Citations4

Human-Computer Interaction Techniques for Explainable Artificial Intelligence Systems

  • Mar 26, 2024
  • Research & Review: Machine Learning and Cloud Computing
  • S Tharun Anand Reddy
  • Research Article
  • Citations51

Predictive modeling in reproductive medicine: Where will the future of artificial intelligence research take us?

  • Nov 01, 2020
  • Fertility and Sterility
  • Carol Lynn Curchoe +18
  • Research Article
  • Citations44

Transparency in AI Decision Making: A Survey of Explainable AI Methods and Applications

  • Jan 19, 2024
  • Advances in Robotic Technology
  • Jain R
  • Preprint Article

User Experience and Trust Improvement Evaluation on Healthcare oriented Explainable Artificial Intelligence Interventions: Systematic Review (Preprint)

  • Feb 25, 2025
  • Samantha Cramer +8
  • Research Article

Advancing Trustworthy AI: Leveraging Explainable AI (XAI) to Drive Safer, Fairer, and More Reliable Intelligent Systems for Next-Generation Technological Innovation

  • Oct 31, 2024
  • International Journal for Research in Applied Science and Engineering Technology
  • Aadhith Rajinikanth
  • Research Article
  • Citations124

A review of explainable and interpretable AI with applications in COVID-19 imaging.

  • Dec 07, 2021
  • Medical physics
  • Jordan D Fuhrman +5
  • Research Article
  • Citations1

Democratizing public-impact algorithms: Advancing equitable and explainable AI systems for decision-making in U.S. health, finance, and education sectors

  • Aug 12, 2025
  • International Journal of Management & Entrepreneurship Research
  • Farouk G Adewumi +2
  • Research Article
  • Citations13

Artificial intelligence hallucinations in anaesthesia: Causes, consequences and countermeasures.

  • Jun 07, 2024
  • Indian journal of anaesthesia
  • Prakash Gondode +2
  • Discussion

Unveiling the black box: imperative for explainable AI in cardiovascular disease (CVD) prevention–author reply

  • Jul 01, 2024
  • The Lancet Regional Health - Western Pacific
  • Mayank Dalakoti +2
  • Research Article
  • Citations12

Use of explainable AI to interpret the results of NLP models for sentimental analysis

  • Jul 01, 2024
  • Indonesian Journal of Electrical Engineering and Computer Science
  • Vijaykumar Bidve +7
  • Research Article
  • Citations10

СТРАТЕГИИ ИНТЕЛЛЕКТА И ЕГО ОНТОЛОГИИ: ПОПЫТКА РАЗОБРАТЬСЯ

  • Jan 01, 2019
  • Ontology of Designing
  • N.М Borgest
  • PDF
  • Discussion
  • Citations11

Artificial intelligence to complement rather than replace radiologists in breast screening

  • Jun 21, 2022
  • The Lancet Digital Health
  • Sian Taylor-Phillips +1
  • Book Chapter
  • Citations2

A Process-Oriented Framework for Regulating Artificial Intelligence Systems

  • Jan 01, 2022
  • Andrew Stranieri +1
  • PDF
  • Research Article
  • Citations11

Human-centric and semantics-based explainable event detection: a survey

  • Jun 22, 2023
  • Artificial Intelligence Review
  • Taiwo Kolajo +1
  • Research Article

ИСКУССТВЕННЫЙ ИНТЕЛЛЕКТ КАК ФАКТОР ТРАНСФОРМАЦИИ ПРАВОВОЙ ДЕЙСТВИТЕЛЬНОСТИ: ВОПРОСЫ ОТВЕТСТВЕННОСТИ

  • Jan 01, 2024
  • Vestnik Tomskogo gosudarstvennogo universiteta
  • S.S Zenin +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.