ECAI 2004 Conference Paper

[full paper]

Outlier Detection using Disjunctive Logic Programming

Fabrizio Angiulli, Rachel Ben-Eliyahu - Zohary, Luigi Palopoli

Assume your general knowledge about the world is encoded in a disjunctive logic program P via Answer Set Semantics. Then, assume you get factual evidence about some aspects of the current status of the world encoded in a second disjunctive logic program, say P'. A fundamental question to be answered is the following: Does the general knowledge encoding P agree with the evidence about the world as encoded in P'? In this paper we first define a formal framework suitable to discuss this question and then illustrate how difficult it is to answer that question.

Keywords: Disjunctive Logic Programming, Knowledge Discovery, Outlier Detection

Citation: Fabrizio Angiulli, Rachel Ben-Eliyahu - Zohary, Luigi Palopoli: Outlier Detection using Disjunctive Logic Programming. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.416-419.