DROPS

Document

Short Paper

DOI: 10.4230/OASIcs.DX.2024.27

On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)

Authors: Charles-Maxime Gauriat, Yannick Pencolé, Pauline Ribot, and Gregory Brouillet

Published in: OASIcs, Volume 125, 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)

Abstract

In an industrial maintenance context, degradation diagnosis is the problem of determining the current level of degradation of operating machines based on measurements. With the emergence of Machine Learning techniques, such a problem can now be solved by training a degradation model offline and by using it online. While such models are more and more accurate and performant, they are often black-box and their decisions are therefore not interpretable for human maintenance operators. On the contrary, interpretable ML models are able to provide explanations for the model’s decisions and consequently improves the confidence of the human operator about the maintenance decision based on these models. This paper proposes a new method to quantitatively measure the interpretability of such models that is agnostic (no assumption about the class of models) and that is applied on degradation models. The proposed method requires that the decision maker sets up some high level parameters in order to measure the interpretability of the models and then can decide whether the obtained models are satisfactory or not. The method is formally defined and is fully illustrated on a decision tree degradation model and a model trained with a recent neural network architecture called Multiclass Neural Additive Model.

Cite as

Charles-Maxime Gauriat, Yannick Pencolé, Pauline Ribot, and Gregory Brouillet. On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 27:1-27:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{gauriat_et_al:OASIcs.DX.2024.27,
  author =	{Gauriat, Charles-Maxime and Pencol\'{e}, Yannick and Ribot, Pauline and Brouillet, Gregory},
  title =	{{On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis}},
  booktitle =	{35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
  pages =	{27:1--27:14},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-356-0},
  ISSN =	{2190-6807},
  year =	{2024},
  volume =	{125},
  editor =	{Pill, Ingo and Natan, Avraham and Wotawa, Franz},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.27},
  URN =		{urn:nbn:de:0030-drops-221196},
  doi =		{10.4230/OASIcs.DX.2024.27},
  annote =	{Keywords: XAI, Interpretability, multiclass supervised learning, degradation diagnosis}
}

Search Results

Documents authored by Gauriat, Charles-Maxime

On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)

Abstract

Cite as

Thanks for your feedback!

Could not send message