A parallel ILP algorithm that incorporates incremental batch learning
Nuno A. Fonseca, Rui Carlos Camacho, Fernado Silva · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · 2003
In this paper we tackle the problems of eciency and scala- bility faced by Inductive Logic Programming (ILP) systems. We propose the use of parallelism to improve eciency and the use of an incremental batch learning to address the scalability problem. We describe a novel parallel algorithm that incorporates into ILP the method of incremen- tal batch learning. The theoretical complexity of the algorithm indicates that a linear speedup can be achieved.