Abstract
We present algorithms that learn certain classes of function-free recursive logic programs in polynomial time from equivalence queries. In particular, we show that a single k-ary recursive constant-depth determinate clause is learnable. Two-clause programs consisting of one learnable recursive clause and one constant-depth determinate non-recursive clause are also learnable, if an additional ``basecase'' oracle is assumed. These results immediately imply the pac-learnability of these classes. Although these classes of learnable recursive programs are very constrained, it is shown in a companion paper that they are maximally general, in that generalizing either class in any natural way leads to a computationally difficult learning problem. Thus, taken together with its companion paper, this paper establishes a boundary of efficient learnability for recursive logic programs.
Cited by
24 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Generalizable synthesis through unification;Proceedings of the ACM on Programming Languages;2021-10-20
2. SynGuar: guaranteeing generalization in programming by example;Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering;2021-08-18
3. Complexity parameters for first order classes;Machine Learning;2006-05-08
4. Prediction-hardness of acyclic conjunctive queries;Theoretical Computer Science;2005-12
5. Generalization Behaviour of Alkemic Decision Trees;Inductive Logic Programming;2005