Communication Efficient Construction of Decision Trees Over Heterogeneously Distributed Data

Authors:
Chris Giannella;Kun Liu;Todd Olsen;Hillol Kargupta
Affiliations:
University of Maryland Baltimore County, Baltimore, MD;University of Maryland Baltimore County, Baltimore, MD;University of Maryland Baltimore County, Baltimore, MD;University of Maryland Baltimore County, Baltimore, MD
Venue:
ICDM '04 Proceedings of the Fourth IEEE International Conference on Data Mining
Year:
2004

Citing 0
Cited 11

Random Projection-Based Multiplicative Data Perturbation for Privacy Preserving Distributed Data Mining

IEEE Transactions on Knowledge and Data Engineering
A privacy-preserving technique for Euclidean distance-based mining algorithms using Fourier-related transforms

The VLDB Journal — The International Journal on Very Large Data Bases
Induction of multiclass multifeature split decision trees from distributed data

Pattern Recognition
PLANET: massively parallel learning of tree ensembles with MapReduce

Proceedings of the VLDB Endowment
A collaborative distributed privacy-sensitive decision support system for monitoring heterogeneous data sources

CTS'05 Proceedings of the 2005 international conference on Collaborative technologies and systems
Distributed threshold querying of general functions by a difference of monotonic representation

Proceedings of the VLDB Endowment
From centralized to distributed decision tree induction using CHAID and fisher's linear discriminant function algorithms

Intelligent Decision Technologies
Distributed learning with data reduction

Transactions on computational collective intelligence IV
Implementation of a distributed data mining system

ICCS'05 Proceedings of the 5th international conference on Computational Science - Volume Part III
Performance evaluation of an agent based distributed data mining system

AI'05 Proceedings of the 18th Canadian Society conference on Advances in Artificial Intelligence
A generic and distributed privacy preserving classification method with a worst-case privacy guarantee

Distributed and Parallel Databases

Quantified Score

Hi-index	0.00

Visualization

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.