{"type":"ScholarlyArticle","title":"Leveraging Argumentation for Generating Robust Sample-based Explanations","authors":[{"name":"Leila Amgoud","slug":"leila-amgoud","given":"Leila","family":"Amgoud","affiliation":""},{"name":"Philippe Muller","slug":"philippe-muller","given":"Philippe","family":"Muller","affiliation":""},{"name":"Henri Trenquier","slug":"henri-trenquier","given":"Henri","family":"Trenquier","affiliation":""}],"abstract":"Explaining predictions made by inductive classifiers has become crucial with the rise of complex models acting more and more as black-boxes. \r\nAbductive explanations are one of the most popular types of explanations that are provided for the purpose. They highlight feature-values that  \r\nare sufficient for making predictions. In the literature, they are generated by exploring the whole feature space, which is unreasonable in practice. \r\nThis paper solves the problem by introducing explanation functions that generate abductive explanations from a sample of instances. It shows \r\nthat such functions should be defined with great care since they cannot satisfy two desirable properties at the same time, namely existence of \r\nexplanations for every individual decision (success) and correctness of explanations (coherence). The paper provides a parameterized family of \r\nargumentation-based explanation functions, each of which satisfies one of the two properties. It studies their formal properties and their experimental \r\nbehaviour on different datasets.","doi":"10.24963/ijcai.2023/346","url":"https://ijcai.org/proceedings/2023/346","pdf":"https://ijcai.org/proceedings/2023/0346.pdf","markdown":"https://ijcai.org/proceedings/2023/346.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/346","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":346,"pages":{"first":3104,"last":3111},"keywords":["AI Ethics, Trust, Fairness: ETF: Explainability and interpretability","Knowledge Representation and Reasoning: KRR: Argumentation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}