Dynamic Ensemble Selection with Probabilistic Classifier Chains
Abstract
Dynamic ensemble selection (DES) is the problem of finding, given an input $\mathbf{x }$ , a subset of models among the ensemble that achieves the best possible prediction accuracy. Recent studies have reformulated the DES problem as a multi-label classification problem and promising performance gains have been reported. However, their approaches may converge to an incorrect, and hence suboptimal, solution as they don’t optimize the true - but non standard - loss function directly. In this paper, we show that the label dependencies have to be captured explicitly and propose a DES method based on Probabilistic Classifier Chains. Experimental results on 20 benchmark data sets show the effectiveness of the proposed method against competitive alternatives, including the aforementioned multi-label approaches. This study is reproducible and the source code has been made available online ( https://github.com/naranil/pcc_des ).
Cite
Text
Narassiguin et al. "Dynamic Ensemble Selection with Probabilistic Classifier Chains." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017. doi:10.1007/978-3-319-71249-9_11Markdown
[Narassiguin et al. "Dynamic Ensemble Selection with Probabilistic Classifier Chains." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017.](https://mlanthology.org/ecmlpkdd/2017/narassiguin2017ecmlpkdd-dynamic/) doi:10.1007/978-3-319-71249-9_11BibTeX
@inproceedings{narassiguin2017ecmlpkdd-dynamic,
title = {{Dynamic Ensemble Selection with Probabilistic Classifier Chains}},
author = {Narassiguin, Anil and Elghazel, Haytham and Aussem, Alex},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2017},
pages = {169-186},
doi = {10.1007/978-3-319-71249-9_11},
url = {https://mlanthology.org/ecmlpkdd/2017/narassiguin2017ecmlpkdd-dynamic/}
}