Improving Anchor-based Explanations - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Improving Anchor-based Explanations

Résumé

Rule-based explanations are a popular method to understand the rationale behind the answers of complex machine learning (ML) classifiers. Recent approaches, such as Anchors, focus on local explanations based on if-then rules that are applicable in the vicinity of a target instance. This has proved effective at producing faithful explanations, yet anchor-based explanations are not free of limitations. These include long overly specific rules as well as explanations of low fidelity. This work presents two simple methods that can mitigate such issues on tabular and textual data. The first approach proposes a careful selection of the discretization method for numerical attributes in tabular datasets. The second one applies the notion of pertinent negatives to explanations on textual data. Our experimental evaluation shows the positive impact of our contributions on the quality of anchor-based explanations.
Fichier principal
Vignette du fichier
cikm2020.pdf (631.16 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03133223 , version 1 (05-02-2021)

Identifiants

Citer

Julien Delaunay, Luis Galárraga, Christine Largouët. Improving Anchor-based Explanations. CIKM 2020 - 29th ACM International Conference on Information and Knowledge Management, Oct 2020, Galway / Virtual, Ireland. pp.3269-3272, ⟨10.1145/3340531.3417461⟩. ⟨hal-03133223⟩
91 Consultations
343 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More