Using Partitioning to Speed Up Speci c-to-General Rule Induction

RISE (Domingos 1995; in press) is a rule induction algorithm that proceeds by gradually generalizing rules, starting with one rule per example. This has several advantages compared to the more common strategy of gradually specializing initially null rules, and has been shown to lead to signi cant accuracy gains over algorithms like C4.5RULES and CN2 in a large number of application domains. However, RISE's running time (like that of other rule induction algorithms) is quadratic in the number of examples, making it unsuitable for processing very large databases. This paper studies the use of partitioning to speed up RISE, and compares it with the wellknown method of windowing. The use of partitioning in a speci c-to-general induction setting creates synergies that would not be possible with a general-to-speci c system. Partitioning often reduces running time and improves accuracy at the same time. In noisy conditions, the performance of windowing deteriorates rapidly, while that of partitioning remains stable.