Towards Generating Explanations for ASP-Based Link Analysis using Declarative Program Transformations
This work addresses the need for transparency in AI systems by providing explanations for link analysis, which is incremental as it builds on existing ASP methods for explicative prediction.
The paper tackles the problem of generating explanations for link analysis tasks like link prediction and anomalous link discovery in social networks using Answer Set Programming (ASP), proposing a novel method based on declarative program transformations to produce offline justifications, with demonstrated efficacy in an application including domain knowledge.
The explication and the generation of explanations are prominent topics in artificial intelligence and data science, in order to make methods and systems more transparent and understandable for humans. This paper investigates the problem of link analysis, specifically link prediction and anomalous link discovery in social networks using the declarative method of Answer set programming (ASP). Applying ASP for link prediction provides a powerful declarative approach, e.g., for incorporating domain knowledge for explicative prediction. In this context, we propose a novel method for generating explanations - as offline justifications - using declarative program transformations. The method itself is purely based on syntactic transformations of declarative programs, e.g., in an ASP formalism, using rule instrumentation. We demonstrate the efficacy of the proposed approach, exemplifying it in an application on link analysis in social networks, also including domain knowledge.