HIBoost: A hubness-aware ensemble learning algorithm for high-dimensional imbalanced data classification

Wu, Qin; Lin, Yaping; Zhu, Tuanfei; Zhang, Yue

doi:10.3233/jifs-190821

Cited by 7 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Žuvela et al also favor ensemble learning approaches for competing objectives and imbalanced situations [ 16 ]. Ensemble learning approaches constitute a current field of development, e.g., a new algorithm (HIBoost) applies a discount factor, which restricts the updating of weights, and hence the risk of overfitting is reduced [ 17 ]. Sets of simultaneous classifiers are also suitable to generate separation frontiers of classes naturally present in bioinformatics.…”

Section: Introductionmentioning

confidence: 99%

Effect of Dataset Size and Train/Test Split Ratios in QSAR/QSPR Multiclass Classification

2021

View full text Add to dashboard Cite

Applied datasets can vary from a few hundred to thousands of samples in typical quantitative structure-activity/property (QSAR/QSPR) relationships and classification. However, the size of the datasets and the train/test split ratios can greatly affect the outcome of the models, and thus the classification performance itself. We compared several combinations of dataset sizes and split ratios with five different machine learning algorithms to find the differences or similarities and to select the best parameter settings in nonbinary (multiclass) classification. It is also known that the models are ranked differently according to the performance merit(s) used. Here, 25 performance parameters were calculated for each model, then factorial ANOVA was applied to compare the results. The results clearly show the differences not just between the applied machine learning algorithms but also between the dataset sizes and to a lesser extent the train/test split ratios. The XGBoost algorithm could outperform the others, even in multiclass modeling. The performance parameters reacted differently to the change of the sample set size; some of them were much more sensitive to this factor than the others. Moreover, significant differences could be detected between train/test split ratios as well, exerting a great effect on the test validation of our models.

show abstract

Section: Introductionmentioning

confidence: 99%

Effect of Dataset Size and Train/Test Split Ratios in QSAR/QSPR Multiclass Classification

2021

View full text Add to dashboard Cite

show abstract

“…O trabalho descrito em [Mani et al 2019] realizou um estudo do potencial do aspecto hubness para a sua aplicac ¸ão nessas tarefas. Os trabalhos [Romaszewski et al 2018, Wu et al 2020] consideraram o aspecto hubness para a classificac ¸ão de conjuntos de dados de outros contextos. Além disso, em [Tomašev et al 2014] o aspecto hubness foi utilizado para a classificac ¸ão de imagens em cenários estáticos.…”

Section: Trabalhos Relacionadosunclassified

“…Enquanto os vetores gerados por camadas mais internas têm maior dimensão. De uma maneira oposta, outras estratégias [Romaszewski et al 2018, Wu et al 2020] têm empregado de maneira eficaz um aspecto inerente aos dados de alta dimensão, denominado hubness, para o desenvolvimento de técnicas que permitem a classificac ¸ão em bancos de dados de alta dimensão. O aspecto hubness consiste na tendência de algumas instâncias de dados, chamadas hubs, ocorrerem com maior frequência nas listas dos K-vizinhos mais próximos de outras instâncias [Mani et al 2019].…”

Section: Introduc ¸ãOunclassified

HubISC: um novo algoritmo baseado em hubness para a classificação de fluxo de dados de imagens

Lima

Faria

Barioni

2022

Anais Do XXXVII Simpósio Brasileiro De Banco De Dados (SBBD 2022)

View full text Add to dashboard Cite

A classificação de fluxo de dados de imagens apresenta vários desafios. Um dos desafios inerente ao domínio de dados de imagens é a alta dimensionalidade dos dados, que pode ocasionar a chamada maldição da dimensionalidade. Trabalhos aplicados em outros contextos empregam de forma eficiente um aspecto, denominado hubness, inerente de dados de alta dimensão. Este artigo apresenta um novo algoritmo para a classificação de fluxo de dados de imagens, que incorpora o aspecto hubness. Os resultados dos experimentos mostram uma boa relação de custo e benefício do algoritmo em termos de eficácia e da porcentagem de instâncias rotuladas em relação aos algoritmos comumente usados para a classificação de fluxos de dados de imagens.

show abstract

“…An adequate definition of the neighborhood also strengthens the boundaries of the positive region, mitigating the hubness issue [7]. This phenomenon occurs when few points in the minority class account for most of the observed neighbor occurrences due to the skewness in the distribution.…”

Section: Introductionmentioning

confidence: 98%

“…This phenomenon occurs when few points in the minority class account for most of the observed neighbor occurrences due to the skewness in the distribution. This issue is faced usually in high-dimensional settings [7].…”

Section: Introductionmentioning

confidence: 99%

FW-SMOTE: A feature-weighted oversampling approach for imbalanced classification

Maldonado

Vairetti

Fernández

et al. 2022

Pattern Recognition

View full text Add to dashboard Cite

HIBoost: A hubness-aware ensemble learning algorithm for high-dimensional imbalanced data classification

Cited by 7 publications

References 1 publication

Effect of Dataset Size and Train/Test Split Ratios in QSAR/QSPR Multiclass Classification

Effect of Dataset Size and Train/Test Split Ratios in QSAR/QSPR Multiclass Classification

HubISC: um novo algoritmo baseado em hubness para a classificação de fluxo de dados de imagens

FW-SMOTE: A feature-weighted oversampling approach for imbalanced classification

Contact Info

Product

Resources

About