Communication Efficient Construction of Decision Trees Over Heterogeneously Distributed Data
Authors:
- 31 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 67-74
Abstract
We present an algorithm designed to efficiently construct a decision tree over heterogeneously distributed data without centralizing. We compare our algorithm against a standard centralized decision tree implementation in terms of accuracy as well as the communication complexity. Our experimental results show that by using only 20% of the communication cost necessary to centralize the data we can achieve trees with accuracy at least 80% of the trees produced by the centralized version.Keywords
This publication has 6 references indexed in Scilit:
- An algorithmic theory of learning: robust concepts and random projection2003
- Decision Tree Induction from Distributed Heterogeneous Autonomous Data Sources2003
- Distributed, Collaborative Data Analysis from Heterogeneous Sites Using a Scalable Evolutionary TechniqueApplied Intelligence, 2002
- An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and RandomizationMachine Learning, 2000
- Learning Rules from Distributed Data2000
- Popular Ensemble Methods: An Empirical StudyJournal of Artificial Intelligence Research, 1999