A repository of real-world datasets for data-driven evolutionary multiobjective optimization

Cheng He,Handing Wang,Ye Tian,Yaochu Jin

doi:10.1007/s40747-019-00126-2

Abstract

Many real-world optimization applications have more than one objective, which are modeled as multiobjective optimization problems. Generally, those complex objective functions are approximated by expensive simulations rather than cheap analytic functions, which have been formulated as data-driven multiobjective optimization problems. The high computational costs of those problems pose great challenges to existing evolutionary multiobjective optimization algorithms. Unfortunately, there have not been any benchmark problems reflecting those challenges yet. Therefore, we carefully select seven benchmark multiobjective optimization problems from real-world applications, aiming to promote the research on data-driven evolutionary multiobjective optimization by suggesting a set of benchmark problems extracted from various real-world optimization applications.

Highlights

The industry applications of Evolutionary multiobjective optimization (EMO) to real-world optimization problems are infrequent, due to the strong assumption that objective function evaluations are accessed. Such objective functions may not exist, instead computationally expensive numerical simulations or costly physical experiments must be performed for evaluations. Such problems driven by data collected in simulations or experiments are formulated as data-driven optimization problems [1], which pose challenges to conventional EMO algorithms
We have proposed a repository of real-world datasets for data-driven EMO
We first give the prosperities of these real-world problems and their approximate Pareto optimal fronts

Summary

Introduction

The first objective denotes the complexity of the network (i.e., the ratio of nonzero weights), and the second objective denotes the classification error rate of the neural network This repository includes six different types of real-world MOPs with different properties, e.g., irregular Pareto fronts/sets, different number of decision variables/objectives, or different problem complexities. For DDMOP6, the obtained approximate Pareto front is simple, and it can be used to reflect the general performance of MOEAs on solving online data-driven multiobjective optimization problems. Since the calculation of HV is ineffective for populations with many objectives, the Monte Carlo estimation method with 1,000,000 sampling points is suggested for populations with more than four objectives for higher computational efficiency

Results

Objective

Conclusion