Answer Set Programming (ASP) is a well-established declarative AI formalism for knowledge representation and reasoning. ASP systems were successfully applied to both industrial and academic problems. Nonetheless, their performance can be improved by embedding domain-specific heuristics into their solving process. However, the development of domain-specific heuristics often requires both a deep knowledge of the domain at hand and a good understanding of the fundamental working principles of the ASP solvers. In this paper, we investigate the use of deep learning techniques to automatically generate domain-specific heuristics for ASP solvers targeting the well-known graph coloring problem. Empirical results show that the idea is promising: the performance of the ASP solver wasp can be improved.
Deep Learning for the Generation of Heuristics in Answer Set Programming: A Case Study of Graph Coloring
Dodaro Carmine;Ricca Francesco
2022-01-01
Abstract
Answer Set Programming (ASP) is a well-established declarative AI formalism for knowledge representation and reasoning. ASP systems were successfully applied to both industrial and academic problems. Nonetheless, their performance can be improved by embedding domain-specific heuristics into their solving process. However, the development of domain-specific heuristics often requires both a deep knowledge of the domain at hand and a good understanding of the fundamental working principles of the ASP solvers. In this paper, we investigate the use of deep learning techniques to automatically generate domain-specific heuristics for ASP solvers targeting the well-known graph coloring problem. Empirical results show that the idea is promising: the performance of the ASP solver wasp can be improved.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.