DynED: Dynamic Ensemble Diversification in Data Stream Classification

TL;DR

DynED introduces a dynamic ensemble method that balances diversity and accuracy to improve classification performance in data streams with concept drift, outperforming existing approaches.

Contribution

The paper proposes a novel MMR-based dynamic ensemble method, DynED, that adaptively selects diverse and accurate components for data stream classification.

Findings

DynED achieves higher average accuracy than five state-of-the-art baselines.

The approach effectively handles concept drift in data streams.

Experimental results on real and synthetic datasets validate its superiority.

Abstract

Ensemble methods are commonly used in classification due to their remarkable performance. Achieving high accuracy in a data stream environment is a challenging task considering disruptive changes in the data distribution, also known as concept drift. A greater diversity of ensemble components is known to enhance prediction accuracy in such settings. Despite the diversity of components within an ensemble, not all contribute as expected to its overall performance. This necessitates a method for selecting components that exhibit high performance and diversity. We present a novel ensemble construction and maintenance approach based on MMR (Maximal Marginal Relevance) that dynamically combines the diversity and prediction accuracy of components during the process of structuring an ensemble. The experimental results on both four real and 11 synthetic datasets demonstrate that the proposed approach (DynED) provides a higher average mean accuracy compared to the five state-of-the-art baselines.