Convex hull-based multi-objective evolutionary computation for maximizing receiver operating characteristics performance

The receiver operating characteristics (ROC) analysis has gained increasing popularity for analyzing the performance of classifiers. In particular, maximizing the convex hull of a set of classifiers in the ROC space, namely ROCCH maximization, is becoming an increasingly important problem. In this work, a new convex hull-based evolutionary multi-objective algorithm named ETriCM is proposed for evolving neural networks with respect to ROCCH maximization. Specially, convex hull-based sorting with convex hull of individual minima (CH-CHIM-sorting) and extreme area extraction selection (EAE-selection) are proposed as a novel selection operator. Empirical studies on 7 high-dimensional and imbalanced datasets show that ETriCM outperforms various state-of-the-art algorithms including convex hull-based evolutionary multi-objective algorithm (CH-EMOA) and non-dominated sorting genetic algorithm II (NSGA-II).

[1]  Xin Yao,et al.  Convex Hull-Based Multiobjective Genetic Programming for Maximizing Receiver Operating Characteristic Performance , 2015, IEEE Transactions on Evolutionary Computation.

[2]  Beatrice Lazzerini,et al.  Multi-objective genetic fuzzy classifiers for imbalanced and cost-sensitive datasets , 2010, Soft Comput..

[3]  Peter A. Flach,et al.  ROCCER: An Algorithm for Rule Learning Based on ROC Analysis , 2005, IJCAI.

[4]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[5]  Peter A. Flach,et al.  Repairing Concavities in ROC Curves , 2005, IJCAI.

[6]  Hussein A. Abbass,et al.  Speeding Up Backpropagation Using Multiobjective Evolutionary Algorithms , 2003, Neural Computation.

[7]  Francisco Herrera,et al.  A New Multiobjective Evolutionary Algorithm for Mining a Reduced Set of Interesting Positive and Negative Quantitative Association Rules , 2014, IEEE Transactions on Evolutionary Computation.

[8]  Yves Lecourtier,et al.  A multi-model selection framework for unknown and/or evolutive misclassification cost problems , 2010, Pattern Recognit..

[9]  Mark Johnston,et al.  Evolving Diverse Ensembles Using Genetic Programming for Classification With Unbalanced Data , 2013, IEEE Transactions on Evolutionary Computation.

[10]  Xin Yao,et al.  Multiobjective genetic programming for maximizing ROC performance , 2014, Neurocomputing.

[11]  Ujjwal Maulik,et al.  A Survey of Multiobjective Evolutionary Algorithms for Data Mining: Part I , 2014, IEEE Transactions on Evolutionary Computation.

[12]  David P. Dobkin,et al.  Finding Extremal Polygons , 1985, SIAM J. Comput..

[13]  Saúl Zapotecas Martínez,et al.  A novel diversification strategy for multi-objective evolutionary algorithms , 2010, GECCO '10.

[14]  Ye Tian,et al.  An Efficient Approach to Nondominated Sorting for Evolutionary Multiobjective Optimization , 2015, IEEE Transactions on Evolutionary Computation.

[15]  Licheng Jiao,et al.  Multiobjective optimization of classifiers by means of 3D convex-hull-based evolutionary algorithms , 2014, Inf. Sci..

[16]  Bernhard Sendhoff,et al.  Generalization Improvement in Multi-Objective Learning , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[17]  Ross Bettinger,et al.  Cost-Sensitive Classifier Selection Using the ROC Convex Hull Method , 2022 .

[18]  Peter A. Flach,et al.  Learning Decision Trees Using the Area Under the ROC Curve , 2002, ICML.

[19]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[20]  Yong Wang,et al.  A new evolutionary multi-objective algorithm for convex hull maximization , 2015, 2015 IEEE Congress on Evolutionary Computation (CEC).

[21]  Tom Fawcett,et al.  Robust Classification for Imprecise Environments , 2000, Machine Learning.

[22]  Zoran Bosnic,et al.  ROC analysis of classifiers in machine learning: A survey , 2013, Intell. Data Anal..

[23]  Beatrice Lazzerini,et al.  A new multi-objective evolutionary algorithm based on convex hull for binary classifier optimization , 2007, 2007 IEEE Congress on Evolutionary Computation.

[24]  Tom Fawcett.  PRIE: a system for generating rulelists to maximize ROC performance , 2008, Data Mining and Knowledge Discovery.

[25]  Indraneel Das,et al.  Nonlinear Multicriteria Optimization and Robust Optimality , 1997 .

[26]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[27]  Kalyanmoy Deb,et al.  A Unified Evolutionary Optimization Procedure for Single, Multiple, and Many Objectives , 2016, IEEE Transactions on Evolutionary Computation.

[28]  Indraneel Das.  On characterizing the “knee” of the Pareto curve based on Normal-Boundary Intersection , 1999 .

[29]  Tapabrata Ray,et al.  A Decomposition-Based Evolutionary Algorithm for Many Objective Optimization , 2015, IEEE Transactions on Evolutionary Computation.

[30]  Peter A. Flach.  The Geometry of ROC Space: Understanding Machine Learning Metrics through ROC Isometrics , 2003, ICML.

[31]  Christian Gagné,et al.  Multi-objective evolutionary optimization for generating ensembles of classifiers in the ROC space , 2012, GECCO '12.

[32]  Ronald L. Graham,et al.  An Efficient Algorithm for Determining the Convex Hull of a Finite Planar Set , 1972, Inf. Process. Lett..