mlsanityData to 14 Oct 2026

Towards a general framework for improving the performance of classifiers using XAI methods

arXiv 2403.10373 ↗First posted 15 Mar 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern Artificial Intelligence (AI) systems, especially Deep Learning (DL) models, poses challenges in understanding their inner workings by AI researchers. eXplainable Artificial Intelligence (XAI) inspects internal mechanisms of AI models providing explanations about their decisions. While current XAI research predominantly concentrates on explaining AI systems, there is a growing interest in using XAI techniques to automatically improve the performance of AI systems themselves. This paper proposes a general framework for automatically improving the performance of pre-trained DL classifiers using XAI methods, avoiding the computational overhead associated with retraining complex models from scratch. In particular, we outline the possibility of two different learning strategies for implementing this architecture, which we will call auto-encoder-based and encoder-decoder-based, and discuss their key aspects.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 15 Mar 2024.

Builds on

14 of 24 references.

References · 14

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 294
  3. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 250
  4. 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 142
  5. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  6. 2018Attention Branch Network: Learning of Attention Mechanism for Visual Explanationcited by 109
  7. 2019Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruningcited by 89
  8. 2019Incorporating Priors with Feature Attribution on Text Classificationcited by 68
  9. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  10. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  11. 2019Embedding Human Knowledge into Deep Neural Network via Attention Mapcited by 33
  12. 2023Learning with Explanation Constraintscited by 8
2 more
  1. 2022Impact of Feedback Type on Explanatory Interactive Learningcited by 7
  2. 2023Strategies to exploit XAI to improve classification systemscited by 7

Built on by

Not cited yet.