A comparison of pruning methods for relational concept learning
Johannes Fürnkranz · 1994
Pre-Pruning and Post-Pruning are two standard methods of dealing with noise in concept learning. Pre-Pruning methods are very efficient, while Post-Pruning methods typically are more accurate, but much slower, because they have to generate an overly specific concept description first. We have experimented with a variety of pruning methods, including two new methods that try to combine and integrate pre- and postpruning in order to achieve both accuracy and efficiency. This is verified with test series in a chess position classification task. 1 Introduction Inductive Logic Programming (ILP) or Relational Learning has established itself as one of the major research areas in the field of Machine Learning [Muggleton, 1992, Lavrac and Dzeroski, 1993]. The ability to define concepts from data distributed in separate relational tables makes ILP methods particularly appropriate for learning from relational databases (see e.g. [Dzeroski and Lavrac, 1993]). However, data from real-world problem...