Journal of Big Data

Table 15 Computational time (seconds) of the boosting algorithms

From: Boosting methods for multi-class imbalanced data classification: an experimental review

Dataset	Algorithm
Dataset	AdaBoost.MH	SAMME	CatBoost	LogitBoost	GradientBoost	XGBoost	MEBoost	SMOTEBoost	RUSBoost	LightGBM	AdaC1	AdaC2	AdaC3	AdaCost
Wine	0.01	0.01	0.79	0.85	0.35	0.03	1.37	0.02	0.72	0.06	0.02	0.01	0.01	0.01
Hayes-Roth	0.01	0.34	0.17	0.81	0.66	0.02	1.45	1.07	0.50	0.06	0.01	0.02	0.01	0.01
Contraceptive	1.11	0.57	0.39	4.53	1.81	0.08	7.41	16.11	1.17	0.16	0.45	0.57	0.57	0.71
Pen-based	0.27	1.04	2.65	7.19	3.62	0.20	27.90	1.26	1.74	1.40	0.32	0.36	0.32	0.41
Vertebral column	0.02	0.54	0.65	1.21	0.54	0.03	3.08	5.45	0.72	0.13	0.02	0.02	0.01	0.02
New thyroid	0.01	0.01	0.48	0.87	0.38	0.02	0.56	4.91	0.52	0.05	0.01	0.01	0.02	0.01
Dermatology	0.08	0.71	0.47	2.63	1.02	0.07	2.42	7.20	1.18	0.51	0.05	0.06	0.33	0.08
Balance scale	0.75	0.40	0.63	1.13	1.22	0.04	5.59	14.67	0.89	0.11	0.62	0.55	0.46	0.55
Glass	0.05	0.36	0.71	1.65	0.87	0.05	2.95	3.46	0.65	0.11	0.05	0.06	0.06	0.06
Heart	0.17	0.44	0.44	1.74	1.00	0.53	14.87	9.10	0.69	0.09	0.17	0.30	1.20	0.13
Car evaluation	0.41	0.70	0.45	1.91	1.85	0.08	5.93	89.18	0.99	0.13	0.07	0.11	0.80	0.08
Thyroid	9.63	2.69	2.48	6.08	2.18	0.35	1.86	Hours	1.44	0.48	1.35	2.58	0.93	2.91
Yeast	1.26	0.79	1.22	6.35	4.79	0.32	24.84	20.33	0.91	0.90	0.27	0.23	0.32	0.41
Page blocks	2.89	3.94	2.75	12.19	4.05	0.40	14.66	116.07	1.22	0.31	1.57	1.63	1.66	8.49
Shuttle	0.14	9.40	8.64	58.01	74.24	3.31	331.38	Hours	10.02	0.15	0.06	0.06	0.06	0.06
Average	1.12	1.46	1.53	7.14	6.57	0.37	29.75	Hours	1.56	0.31	0.33	0.44	0.45	0.93

The best comptional time is shown in italic for each dataset

Back to article page