Skip to Main content Skip to Navigation
Conference papers

Improving Anchor-based Explanations

Julien Delaunay 1 Luis Galárraga 1 Christine Largouët 1, 2
1 LACODAM - Large Scale Collaborative Data Mining
Inria Rennes – Bretagne Atlantique , IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
Abstract : 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.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-03133223
Contributor : Luis Galárraga Connect in order to contact the contributor
Submitted on : Friday, February 5, 2021 - 5:57:19 PM
Last modification on : Wednesday, November 3, 2021 - 8:09:40 AM
Long-term archiving on: : Friday, May 7, 2021 - 8:28:58 AM

File

cikm2020.pdf
Files produced by the author(s)

Identifiers

Citation

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⟩

Share

Metrics

Les métriques sont temporairement indisponibles