Multi-Context Systems with Preferences

Abstract

This paper presents an extension of the Multi-Context Systems (MCS) framework to allow the encoding of preferences at the level of the contexts. The work is motivated by the observation that a naive use of preference logics at a context level in an MCS can lead to undesirable outcomes, such as inco nsistency of the MCS. To address this issue, the paper introduces the notion of ranked logics, suitable for use with multiple sources of preferences, and employs them in the definition of weakly and strongly-preferred equilibria in a Multi-Context Systems with Preferences (MCSP) framework. The usefulness of MCSP is demonstrated in two applications: modeling distributed configuration problems and finding explanations for distributed abductive diagnosis problems.