Enumerating semantics extensions in abstract argumentation is generally an intractable problem. For preferred semantics four algorithms have been recently proposed, AspartixM, NAD-Alg, PrefSAT and SCC-P, with significant runtime variations. This work is a first comprehensive exploration of the graph features and of their impact on the execution time of state-of-the-art preferred extensions enumeration algorithms. Following other areas of AI, we exploit empirical performance models, predictive models that relate instance features and algorithms performance. The result is an approach able to select the “best” algorithm for any Dung's argumentation framework with an accuracy, on the average, of the 80%. Moreover, we show that an algorithm selection approach based on classification can select the fastest algorithm in about the double of the number of cases where the most efficient algorithm outperforms the other ones (SCC-P), and about three times the number of cases of the second most efficient algorithm (PrefSAT).
|Title of host publication||Computational Models of Argument|
|Subtitle of host publication||Proceedings of COMMA 2014|
|Number of pages||12|
|ISBN (Electronic)|| 9781614994367|
|ISBN (Print)|| 9781614994350|
|Publication status||Published - 2014|
|Name||Frontiers in Artificial Intelligence and Applications|