Adaptive regularized ensemble for evolving data stream classification

doi:10.1016/j.patrec.2024.02.026

2024-04-01

PRE

Aldo Marcelo Paim *

Fabrício Enembreck

DOI：10.1016/j.patrec.2024.02.026

原文链接

原文求助

摘要

En 中文

Extracting knowledge from data streams requires fast incremental algorithms that are able to handle unlimited processing and ever-changing data with finite memory. A strategy for this challenge is the use of ensembles owing to their ability to tackle concept drift and achieve highly accurate predictions. However, ensembles often require a lot of computational resources. In this study, we propose a novel ensemble-based classification algorithm for data streams, Adaptive Regularized Ensemble (ARE), with low demand for computational resources. The algorithm combines strategies that contribute to high prediction accuracy using only incorrectly classified instances into the training step, random-sized feature subspace for each ensemble element and classifier selection for final ensemble voting. After an extensive experimental study, ARE exhibited high predictive performance and outperformed state-of-the-art ensembles on data streams for real and synthetic datasets while requiring a low processing time and memory consumption.

Keyword:

Data stream mining

Regularized ensemble

Ensemble learning

Concept drift

Random subspaces