EUSBoost: Enhancing ensembles for highly imbalanced data-sets by evolutionary undersampling

By Mikel Galar, Alberto Fernández, Edurne Barrenechea Tartas, Francisco Herrera. Pattern Recognition, 2013

399 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/c1a318888e7f718654ed8b64b852dd951563b309

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

A Survey of Predictive Modeling on Imbalanced Domains (2016, background): “Evolutionary under-sampling has also been combined with boosting [Galar et al. 2013].”
Ensemble learning: A survey (2018, methodology): “The prediction performance can be further improved by using the EUSBoost method which leverages evolutionary under-sampling to promote diversity among individual inducers (Galar, Fernández, Barrenechea, & Herrera, 2013).”
A review of microarray datasets and applied feature selection methods (2014, positive): “In recent years, ensemble of classifiers has arisen as a possible solution to the class imbalance problem, attracting great interest among researchers [41,42], in several cases combined with preprocessing techniques such as SMOTE.”
A Systematic Review on Imbalanced Data Challenges in Machine Learning (2019, background): “(1) The major challenge occurs while completing the objective of resampling the classes, i.e., there are chances of over-fitting in the majority class while oversampling and information loss from the minority class in case of undersampling (Galar et al. 2013).”
MLSMOTE: Approaching imbalanced multilabel learning through synthetic instance generation (2015, methodology): “The use of ensembles in imbalanced classification was recently reviewed in [41], and some specific algorithms are proposed in [42].”
Dual autoencoders features for imbalance classification problem (2016, methodology): “Instead of random undersampling, the EUSBoost uses evolutionary undersampling to enhance accuracies of base classifiers.”
Boosting methods for multi-class imbalanced data classification: an experimental review (2020, methodology): “M2 Using the sampling probability distribution for ranking the minority class samples 2010 AOSO-LogitBoost [48] One versus one version of LogitBoost for multiclass classification Solving the difficulties of dense Hessian Matrix in Logistic loss by utilizing vector tree and adaptive block coordinate ”