NormEnsembleXAI: Unveiling the Strengths and Weaknesses of XAI Ensemble Techniques

Weronika Hryniewska-Guzik, Bartosz Sawicki, Przemysław Biecek
1/30/2024
cs.LGcs.AIcs.CV

No official code found. Best implementation: Hryniewska/EnsembleXAI (9 stars, BSD-3-Clause, last commit 2024-10-15).

Abstract

This paper presents a comprehensive comparative analysis of explainable artificial intelligence (XAI) ensembling methods. Our research brings three significant contributions. Firstly, we introduce a novel ensembling method, NormEnsembleXAI, that leverages minimum, maximum, and average functions in conjunction with normalization techniques to enhance interpretability. Secondly, we offer insights into the strengths and weaknesses of XAI ensemble methods. Lastly, we provide a library, facilitating the practical implementation of XAI ensembling, thus promoting the adoption of transparent and interpretable deep learning models.

View on arXivView PDF

Code Implementations(1)

Hryniewska/EnsembleXAICommunity100%
BSD-3-Clause

EnsembleXAI simplifies aggregation of explanations, normalization and assessment for enhanced model explainability.

92HTML, PythonOct 30, 20232 years agoBSD-3-Clause

Cite this paper

@article{hryniewskaguzik2024normensemblexai,
  title  = {NormEnsembleXAI: Unveiling the Strengths and Weaknesses of XAI Ensemble Techniques},
  author = {Weronika Hryniewska-Guzik and Bartosz Sawicki and Przemysław Biecek},
  year   = {2024},
  eprint = {2401.17200},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2401.17200v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2401.17200.svg)](https://codeofpaper.com/paper/2401.17200)

Discussion