On the Complexity of Inductively Learning Guarded Rules [article]

Andrei Draghici, Georg Gottlob, Matthias Lanzinger
2021 arXiv   pre-print
We investigate the computational complexity of mining guarded clauses from clausal datasets through the framework of inductive logic programming (ILP). We show that learning guarded clauses is NP-complete and thus one step below the σ^P_2-complete task of learning Horn clauses on the polynomial hierarchy. Motivated by practical applications on large datasets we identify a natural tractable fragment of the problem. Finally, we also generalise all of our results to k-guarded clauses for constant k.
arXiv:2110.03624v1 fatcat:qhjretsmqzhvpb2emrh4nxrb6u