Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kantz, Benedikt, Staudinger, Clemens, Feilmayr, Christoph, Wachlmayr, Johannes, Haberl, Alexander, Schuster, Stefan, Pernkopf, Franz
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.09127
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913528729829376
author Kantz, Benedikt
Staudinger, Clemens
Feilmayr, Christoph
Wachlmayr, Johannes
Haberl, Alexander
Schuster, Stefan
Pernkopf, Franz
author_facet Kantz, Benedikt
Staudinger, Clemens
Feilmayr, Christoph
Wachlmayr, Johannes
Haberl, Alexander
Schuster, Stefan
Pernkopf, Franz
contents eXplainable Artificial Intelligence (XAI) aims at providing understandable explanations of black box models. In this paper, we evaluate current XAI methods by scoring them based on ground truth simulations and sensitivity analysis. To this end, we used an Electric Arc Furnace (EAF) model to better understand the limits and robustness characteristics of XAI methods such as SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), as well as Averaged Local Effects (ALE) or Smooth Gradients (SG) in a highly topical setting. These XAI methods were applied to various types of black-box models and then scored based on their correctness compared to the ground-truth sensitivity of the data-generating processes using a novel scoring evaluation methodology over a range of simulated additive noise. The resulting evaluation shows that the capability of the Machine Learning (ML) models to capture the process accurately is, indeed, coupled with the correctness of the explainability of the underlying data-generating process. We furthermore show the differences between XAI methods in their ability to correctly predict the true sensitivity of the modeled industrial process.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09127
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robustness of Explainable Artificial Intelligence in Industrial Process Modelling
Kantz, Benedikt
Staudinger, Clemens
Feilmayr, Christoph
Wachlmayr, Johannes
Haberl, Alexander
Schuster, Stefan
Pernkopf, Franz
Machine Learning
eXplainable Artificial Intelligence (XAI) aims at providing understandable explanations of black box models. In this paper, we evaluate current XAI methods by scoring them based on ground truth simulations and sensitivity analysis. To this end, we used an Electric Arc Furnace (EAF) model to better understand the limits and robustness characteristics of XAI methods such as SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), as well as Averaged Local Effects (ALE) or Smooth Gradients (SG) in a highly topical setting. These XAI methods were applied to various types of black-box models and then scored based on their correctness compared to the ground-truth sensitivity of the data-generating processes using a novel scoring evaluation methodology over a range of simulated additive noise. The resulting evaluation shows that the capability of the Machine Learning (ML) models to capture the process accurately is, indeed, coupled with the correctness of the explainability of the underlying data-generating process. We furthermore show the differences between XAI methods in their ability to correctly predict the true sensitivity of the modeled industrial process.
title Robustness of Explainable Artificial Intelligence in Industrial Process Modelling
topic Machine Learning
url https://arxiv.org/abs/2407.09127