On-the-Fly Ensemble Pruning in Evolving Data Streams

TL;DR

This paper introduces CCRP, an on-the-fly ensemble pruning method for evolving data streams that selects the best classifiers per class, reducing memory use while maintaining or improving accuracy.

Contribution

The paper presents CCRP, a novel imbalance-aware ensemble pruning approach for data streams, focusing on class-wise classifier selection during stream processing.

Findings

CCRP reduces memory consumption by 20% to 90%.

The method achieves comparable or better accuracy than existing pruning schemes.

Experiments on real-world and synthetic data validate CCRP's effectiveness.

Abstract

Ensemble pruning is the process of selecting a subset of componentclassifiers from an ensemble which performs at least as well as theoriginal ensemble while reducing storage and computational costs.Ensemble pruning in data streams is a largely unexplored area ofresearch. It requires analysis of ensemble components as they arerunning on the stream, and differentiation of useful classifiers fromredundant ones. We present CCRP, an on-the-fly ensemble prun-ing method for multi-class data stream classification empoweredby an imbalance-aware fusion of class-wise component rankings.CCRP aims that the resulting pruned ensemble contains the bestperforming classifier for each target class and hence, reduces the ef-fects of class imbalance. The conducted experiments on real-worldand synthetic data streams demonstrate that different types of en-sembles that integrate CCRP as their pruning scheme consistentlyyield on par or superior performance with 20% to 90% less averagememory consumption. Lastly, we validate the proposed pruningscheme by comparing our approach against pruning schemes basedon ensemble weights and basic rank fusion methods.