Ensemble pruning via an integer programming approach with diversity constraints

TL;DR

This paper introduces an integer programming method for ensemble pruning in binary classification that optimizes classifier selection while maintaining diversity, achieving competitive results efficiently.

Contribution

It presents a novel IP-based ensemble pruning approach with flexible objectives and diversity constraints, outperforming existing methods in efficiency and effectiveness.

Findings

Effective classifier subset selection with diversity constraints

Competitive accuracy compared to existing pruning methods

Scalable solutions for datasets with up to 60,000 data points

Abstract

Ensemble learning combines multiple classifiers in the hope of obtaining better predictive performance. Empirical studies have shown that ensemble pruning, that is, choosing an appropriate subset of the available classifiers, can lead to comparable or better predictions than using all classifiers. In this paper, we consider a binary classification problem and propose an integer programming (IP) approach for selecting optimal classifier subsets. We propose a flexible objective function to adapt to desired criteria of different datasets. We also propose constraints to ensure minimum diversity levels in the ensemble. Despite the general case of IP being NP-Hard, state-of-the-art solvers are able to quickly obtain good solutions for datasets with up to 60000 data points. Our approach yields competitive results when compared to some of the best and most used pruning methods in literature.