Evaluation of summarization schemes for learning in streams

Authors:
Alec Pawling;Nitesh V. Chawla;Amitabh Chaudhary
Affiliations:
University of Notre Dame;University of Notre Dame;University of Notre Dame
Venue:
PKDD'06 Proceedings of the 10th European conference on Principle and Practice of Knowledge Discovery in Databases
Year:
2006

Citing 7
Cited 0

BOAT—optimistic decision tree construction

SIGMOD '99 Proceedings of the 1999 ACM SIGMOD international conference on Management of data
Mining high-speed data streams

Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining
Mining time-changing data streams

Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
A streaming ensemble algorithm (SEA) for large-scale classification

Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
Models and issues in data stream systems

Proceedings of the twenty-first ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Counting inversions in lists

SODA '03 Proceedings of the fourteenth annual ACM-SIAM symposium on Discrete algorithms
Streaming and sublinear approximation of entropy and information distances

SODA '06 Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditional discretization techniques for machine learning, from examples with continuous feature spaces, are not efficient when the data is in the form of a stream from an unknown, possibly changing, distribution. We present a time-and-memory-efficient discretization technique based on computing ε-approximate exponential frequency quantiles, and prove bounds on the worst-case error introduced in computing information entropy in data streams compared to an offline algorithm that has no efficiency constraints. We compare the empirical performance of the technique, using it for feature selection, with (streaming adaptations of) two popular methods of discretization, equal width binning and equal frequency binning, under a variety of streaming scenarios for real and artificial datasets. Our experiments show that ε-approximate exponential frequency quantiles are remarkably consistent in their performance, in contrast to the simple and efficient equal width binning that perform quite well when the streams are from stationary distributions, and quite poorly otherwise.