Divide, Specialize, and Route: A New Approach to Efficient Ensemble Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Piwko, Jakub, Ruciński, Jędrzej, Płudowski, Dawid, Zajko, Antoni, Żak, Patryzja, Zacharecki, Mateusz, Kozak, Anna, Woźnica, Katarzyna
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909660211052544
author Piwko, Jakub
Ruciński, Jędrzej
Płudowski, Dawid
Zajko, Antoni
Żak, Patryzja
Zacharecki, Mateusz
Kozak, Anna
Woźnica, Katarzyna
author_facet Piwko, Jakub
Ruciński, Jędrzej
Płudowski, Dawid
Zajko, Antoni
Żak, Patryzja
Zacharecki, Mateusz
Kozak, Anna
Woźnica, Katarzyna
contents Ensemble learning has proven effective in boosting predictive performance, but traditional methods such as bagging, boosting, and dynamic ensemble selection (DES) suffer from high computational cost and limited adaptability to heterogeneous data distributions. To address these limitations, we propose Hellsemble, a novel and interpretable ensemble framework for binary classification that leverages dataset complexity during both training and inference. Hellsemble incrementally partitions the dataset into circles of difficulty by iteratively passing misclassified instances from simpler models to subsequent ones, forming a committee of specialised base learners. Each model is trained on increasingly challenging subsets, while a separate router model learns to assign new instances to the most suitable base model based on inferred difficulty. Hellsemble achieves strong classification accuracy while maintaining computational efficiency and interpretability. Experimental results on OpenML-CC18 and Tabzilla benchmarks demonstrate that Hellsemble often outperforms classical ensemble methods. Our findings suggest that embracing instance-level difficulty offers a promising direction for constructing efficient and robust ensemble systems.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20814
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Divide, Specialize, and Route: A New Approach to Efficient Ensemble Learning
Piwko, Jakub
Ruciński, Jędrzej
Płudowski, Dawid
Zajko, Antoni
Żak, Patryzja
Zacharecki, Mateusz
Kozak, Anna
Woźnica, Katarzyna
Machine Learning
Ensemble learning has proven effective in boosting predictive performance, but traditional methods such as bagging, boosting, and dynamic ensemble selection (DES) suffer from high computational cost and limited adaptability to heterogeneous data distributions. To address these limitations, we propose Hellsemble, a novel and interpretable ensemble framework for binary classification that leverages dataset complexity during both training and inference. Hellsemble incrementally partitions the dataset into circles of difficulty by iteratively passing misclassified instances from simpler models to subsequent ones, forming a committee of specialised base learners. Each model is trained on increasingly challenging subsets, while a separate router model learns to assign new instances to the most suitable base model based on inferred difficulty. Hellsemble achieves strong classification accuracy while maintaining computational efficiency and interpretability. Experimental results on OpenML-CC18 and Tabzilla benchmarks demonstrate that Hellsemble often outperforms classical ensemble methods. Our findings suggest that embracing instance-level difficulty offers a promising direction for constructing efficient and robust ensemble systems.
title Divide, Specialize, and Route: A New Approach to Efficient Ensemble Learning
topic Machine Learning
url https://arxiv.org/abs/2506.20814