Automated Selection and Configuration of Multi-Label Classification Algorithms with Grammar-Based Genetic Programming

被引:17
作者
de Sa, Alex G. C. [1 ]
Freitas, Alex A. [2 ]
Pappa, Gisele L. [1 ]
机构
[1] Univ Fed Minas Gerais, Comp Sci Dept, Belo Horizonte, MG, Brazil
[2] Univ Kent, Sch Comp, Canterbury, Kent, England
来源
PARALLEL PROBLEM SOLVING FROM NATURE - PPSN XV, PT II | 2018年 / 11102卷
基金
欧盟地平线“2020”;
关键词
Automated machine learning (Auto-ML); Multi-label classification; Grammar-based genetic programming;
D O I
10.1007/978-3-319-99259-4_25
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes Auto-MEKAGGP, an Automated Machine Learning (Auto-ML) method for Multi-Label Classification (MLC) based on the MEKA tool, which offers a number of MLC algorithms. In MLC, each example can be associated with one or more class labels, making MLC problems harder than conventional (single-label) classification problems. Hence, it is essential to select an MLC algorithm and its configuration tailored (optimized) for the input dataset. Auto-MEKAGGP addresses this problem with two key ideas. First, a large number of choices of MLC algorithms and configurations from MEKA are represented into a grammar. Second, our proposed Grammar-based Genetic Programming (GGP) method uses that grammar to search for the best MLC algorithm and configuration for the input dataset. Auto-MEKAGGP was tested in 10 datasets and compared to two well-known MLC methods, namely Binary Relevance and Classifier Chain, and also compared to GA-Auto-MLC, a genetic algorithm we recently proposed for the same task. Two versions of Auto-MEKAGGP were tested: a full version with the proposed grammar, and a simplified version where the grammar includes only the algorithmic components used by GA-Auto-MLC. Overall, the full version of Auto-MEKAGGP achieved the best predictive accuracy among all five evaluated methods, being the winner in six out of the 10 datasets.
引用
收藏
页码:308 / 320
页数:13
相关论文
共 16 条
[1]  
de Sa A. G. C., 2018, TECHNICAL REPORT
[2]   Towards a Method for Automatically Selecting and Configuring Multi-Label Classification Algorithms [J].
de Sa, Alex G. C. ;
Pappa, Gisele L. ;
Freitas, Alex A. .
PROCEEDINGS OF THE 2017 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION (GECCO'17 COMPANION), 2017, :1125-1132
[3]   RECIPE: A Grammar-Based Framework for Automatically Evolving Classification Pipelines [J].
de Sa, Alex G. C. ;
Pinto, Walter Jose G. S. ;
Oliveira, Luiz Otavio V. B. ;
Pappa, Gisele L. .
GENETIC PROGRAMMING, EUROGP 2017, 2017, 10196 :246-261
[4]  
Demsar J, 2006, J MACH LEARN RES, V7, P1
[5]  
Feurer M, 2015, ADV NEUR IN, V28
[6]   Automatic Creation of Machine Learning Workflows with Strongly Typed Genetic Programming [J].
Kren, Tomas ;
Pilat, Matin ;
Neruda, Roman .
INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2017, 26 (05)
[7]   Grammar-based Genetic Programming: a survey [J].
McKay, Robert I. ;
Nguyen Xuan Hoai ;
Whigham, Peter Alexander ;
Shan, Yin ;
O'Neill, Michael .
GENETIC PROGRAMMING AND EVOLVABLE MACHINES, 2010, 11 (3-4) :365-396
[8]   Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science [J].
Olson, Randal S. ;
Bartley, Nathan ;
Urbanowicz, Ryan J. ;
Moore, Jason H. .
GECCO'16: PROCEEDINGS OF THE 2016 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2016, :485-492
[9]  
Otero FEB, 2012, PROCEEDINGS OF THE FOURTEENTH INTERNATIONAL CONFERENCE ON GENETIC AND EVOLUTIONARY COMPUTATION COMPANION (GECCO'12), P93
[10]  
Pedregosa F, 2011, J MACH LEARN RES, V12, P2825