Ordyniak, S., Paesani, G., & Szeider, S. (2023). The Parameterized Complexity of Finding Concise Local Explanations. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23) (pp. 3312–3320). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2023/369
E192-01 - Forschungsbereich Algorithms and Complexity
-
Erschienen in:
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23)
-
ISBN:
978-1-956792-03-4
-
Datum (veröffentlicht):
2023
-
Veranstaltungsname:
32nd International Joint Conference on Artificial Intelligence (IJCAI 2023)
en
Veranstaltungszeitraum:
19-Aug-2023 - 25-Aug-2023
-
Veranstaltungsort:
Macao, China
-
Umfang:
9
-
Verlag:
International Joint Conferences on Artificial Intelligence
-
Keywords:
Knowledge Representation and Reasoning; Computational complexity of reasoning; Explainable/Interpretable machine learning
en
Abstract:
We consider the computational problem of finding a smallest local explanation (anchor) for classifying a given feature vector (example) by a black-box model. After showing that the problem is NP-hard in general, we study various natural restrictions of the problem in terms of problem parameters to see whether these restrictions make the problem fixedparameter tractable or not. We draw a detailed and systematic complexity landscape for combinations of parameters, including the size of the anchor, the size of the anchor’s coverage, and parameters that capture structural aspects of the problem instance, including rank-width, twin-width, and maximum difference.
