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

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 b...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Machine learning Ročník 111; číslo 5; s. 1799 - 1820
Hlavní autoři: Rabold, Johannes, Siebers, Michael, Schmid, Ute
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.05.2022
Springer Nature B.V
Témata:
Algorithms
Arches
Artificial Intelligence
Computer Science
Control
Domains
Logic programming
Machine Learning
Mechatronics
Natural Language Processing (NLP)
Robotics
Simulation and Modeling
Contrastive explanations
Explainable AI
Near miss examples
Inductive logic programming
Relational concepts
ISSN:0885-6125, 1573-0565
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0885-6125
1573-0565
DOI:10.1007/s10994-021-06048-w