Relational-AntMiner: First-Order Rule Discovery with Ant Colony Optimization

Ant colony optimization has been applied to learning sets of propositional rules. In this paper, we introduce a new algorithm, Relational-AntMiner, for learning sets of first-order rules with ant colony optimization. First-order rules are more expressive than traditional propositional rules and in some cases they can provide a more intuitive and accurate concept description. As a case study, we apply Relational-AntMiner to a benchmark relational data set and compare our results with the results obtained by a state-of-the-art first-order rule learning algorithm.