Improving Anchor-based Explanations - Archive ouverte HAL Access content directly
Conference Papers Year :

Improving Anchor-based Explanations


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
Origin : Files produced by the author(s)

Dates and versions

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



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⟩
76 View
288 Download



Gmail Facebook Twitter LinkedIn More