Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

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

Publication

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

Faculty/Chair
Faculty/Professorship
Author
Rabold, Johannes
Title of the Journal
Machine Learning
ISSN
0885-6125
Publisher Information
Springer Science + Business Media B.V : Dordrecht [u.a.]
Year of publication
2021
Volume
111
Language
English
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 Keywords
Maschinelles Lernen
Relation <Mathematik>
Kontrastive Syntax
Beinahe-Unfall
Keywords
Explainable AI
Relational concepts
Contrastive explanations
Inductive logic programming
Near miss examples
DDC Classification
004 Computer science
RVK Classification
SK 130
Peer Reviewed
yes
International Distribution
yes
Type
Article
URI
Activation date
2021-09-30

Permalink: https://fis.uni-bamberg.de/handle/uniba/51715 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.