Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Generating contrastive explanations for inductive logic programming based on a near miss approach

Publikation

Generating contrastive explanations for inductive logic programming based on a near miss approach

Rabold, Johannes; Siebers, Michael; Schmid, Ute (2021): Generating contrastive explanations for inductive logic programming based on a near miss approach, in: Machine Learning, Dordrecht [u.a.]: Springer Science + Business Media B.V, Jg. 111, S. 1799–1820, doi: 10.1007/s10994-021-06048-w.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Rabold, Johannes
Titel der Zeitschrift
Machine Learning
ISSN
0885-6125
Verlagsangabe
Springer Science + Business Media B.V : Dordrecht [u.a.]
Erscheinungsjahr
2021
Jahrgang
111
Sprache(n)
Englisch
DOI
Abstract

In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early AI research, concept understanding can also be improved by the alignment of a given instance for a concept with a similar counterexample. Contrasting a given instance with a structurally similar example which does not belong to the concept highlights what characteristics are necessary for concept membership. Such near misses have been proposed by Winston (Learning structural descriptions from examples, 1970) as efficient guidance for learning in relational domains. We introduce an explanation generation algorithm for relational concepts learned with Inductive Logic Programming (GeNME). The algorithm identifies near miss examples from a given set of instances and ranks these examples by their degree of closeness to a specific positive instance. A modified rule which covers the near miss but not the original instance is given as an explanation. We illustrate GeNME with the well-known family domain consisting of kinship relations, the visual relational Winston arches domain, and a real-world domain dealing with file management. We also present a psychological experiment comparing human preferences of rule-based, example-based, and near miss explanations in the family and the arches domains.

GND-Schlagwort(e)
Maschinelles Lernen
Relation <Mathematik>
Kontrastive Syntax
Beinahe-Unfall
Freie Schlagwort(e)
Explainable AI
Relational concepts
Contrastive explanations
Inductive logic programming
Near miss examples
DDC-Klassifikation
004 Computer science
RVK-Klassifikation
SK 130
Peer Reviewed
ja
Internationale Verbreitung
ja
Dokumenttyp
Artikel in einer Zeitschrift / Postprint
URI
Datum der Freischaltung
30.09.2021

Permalink: https://fis.uni-bamberg.de/handle/uniba/51715 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 15.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.