Publication View

A Survey of Methods for Scaling Up Inductive Algorithms (1999)

Abstract

. One of the defining challenges for the KDD research community is to enable inductive learning algorithms to mine very large databases. By collecting, categorizing, and summarizing existing work on scaling up inductive algorithms, this paper serves to establish common ground for researchers addressing the challenge. We concentrate on algorithms that build decision trees and rule sets, in order to provide focus and specific details; the issues and techniques generalize to other types of data mining. We begin with a discussion of important issues related to scaling up. We highlight similarities among scaling techniques by categorizing them into three main approaches. For each approach, we then describe, compare, and contrast the different constituent techniques, drawing on specific examples from published papers. Finally, we use the preceding analysis to suggest how one should proceed when dealing with a large problem, and where future research efforts should be focused. Keywords: scal...

Publication details

Download	http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.56.3387
Source	http://www.cs.pitt.edu/~foster/scaling-survey.ps
Contributors	CiteSeerX
Repository	CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Keywords	scaling up, inductive learning, decision trees, rule learning
Type	text
Language	English
Relation	10.1.1.40.6757, 10.1.1.50.8204, 10.1.1.11.3107, 10.1.1.42.5440, 10.1.1.49.1062, 10.1.1.27.363, 10.1.1.10.1780, 10.1.1.52.7062, 10.1.1.47.7199, 10.1.1.49.5614, 10.1.1.41.6394, 10.1.1.75.2556, 10.1.1.42.1757, 10.1.1.49.5708, 10.1.1.17.5769, 10.1.1.113.7813, 10.1.1.52.7676, 10.1.1.52.5594, 10.1.1.48.600, 10.1.1.44.5033, 10.1.1.33.1953, 10.1.1.53.4580, 10.1.1.48.6483, 10.1.1.33.2505, 10.1.1.55.6843, 10.1.1.32.8676, 10.1.1.52.8997, 10.1.1.52.1595, 10.1.1.31.8894, 10.1.1.44.6459, 10.1.1.15.2748, 10.1.1.28.3061, 10.1.1.13.2381, 10.1.1.33.309, 10.1.1.28.5494, 10.1.1.113.888, 10.1.1.65.7709, 10.1.1.28.7831, 10.1.1.71.9571, 10.1.1.2.9831, 10.1.1.22.6271, 10.1.1.68.2158, 10.1.1.3.3542, 10.1.1.21.7100, 10.1.1.8.4831, 10.1.1.15.6587, 10.1.1.28.9149, 10.1.1.11.6473, 10.1.1.13.9250, 10.1.1.96.2553, 10.1.1.14.1075, 10.1.1.76.7502, 10.1.1.116.252, 10.1.1.33.1283, 10.1.1.28.8876, 10.1.1.29.1493, 10.1.1.106.1057, 10.1.1.58.8844, 10.1.1.37.1727, 10.1.1.63.4555, 10.1.1.63.5319, 10.1.1.63.6307, 10.1.1.64.4750, 10.1.1.65.5185, 10.1.1.68.6132, 10.1.1.7.5177, 10.1.1.80.9031, 10.1.1.81.9486, 10.1.1.86.9168, 10.1.1.88.8064, 10.1.1.89.7463, 10.1.1.40.81, 10.1.1.96.9110, 10.1.1.111.1513, 10.1.1.113.2805, 10.1.1.115.8375, 10.1.1.115.8799, 10.1.1.119.4596, 10.1.1.123.5796, 10.1.1.126.5567, 10.1.1.43.899, 10.1.1.37.2995, 10.1.1.38.5787, 10.1.1.29.7246, 10.1.1.33.4625, 10.1.1.21.4824, 10.1.1.22.907, 10.1.1.7.6063, 10.1.1.3.2199, 10.1.1.60.8853, 10.1.1.61.6145