Feature Necessity & Relevancy in ML Classifier Explanations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Feature Necessity & Relevancy in ML Classifier Explanations

Résumé

Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction. In some applications, and besides asking for an explanation, it is also critical to understand whether sensitive features can occur in some explanation, or whether a non-interesting feature must occur in all explanations. This paper starts by relating such queries respectively with the problems of relevancy and necessity in logic-based abduction. The paper then proves membership and hardness results for several families of ML classifiers. Afterwards the paper proposes concrete algorithms for two classes of classifiers. The experimental results confirm the scalability of the proposed algorithms.

Dates et versions

hal-04311134 , version 1 (28-11-2023)

Licence

Paternité

Identifiants

Citer

Xuanxiang Huang, Martin Cooper, Antonio Morgado, Jordi Planes, Joao Marques-Silva. Feature Necessity & Relevancy in ML Classifier Explanations. 29th International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS 2023) @ ETAPS 2023, Apr 2023, Paris, France. pp.167-186, ⟨10.1007/978-3-031-30823-9_9⟩. ⟨hal-04311134⟩
18 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More