Neuroevolution for solving multiobjective knapsack problems

Abstract The multiobjective knapsack problem (MOKP) is an important combinatorial problem that arises in various applications, including resource allocation, computer science and finance. When tackling this problem by evolutionary multiobjective optimization algorithms (EMOAs), it has been demonstrated that traditional recombination operators acting on binary solution representations are susceptible to a loss of diversity and poor scalability. To address those issues, we propose to use artificial neural networks for generating solutions by performing a binary classification of items using the information about their profits and weights. As gradient-based learning cannot be used when target values are unknown, neuroevolution is adapted to adjust the neural network parameters. The main contribution of this study resides in developing a solution encoding and genotype-phenotype mapping for EMOAs to solve MOKPs. The proposal is implemented within a state-of-the-art EMOA and benchmarked against traditional variation operators based on binary crossovers. The obtained experimental results indicate a superior performance of the proposed approach. Furthermore, it is advantageous in terms of scalability and can be readily incorporated into different EMOAs.

[1]  Risto Miikkulainen,et al.  A Taxonomy for Artificial Embryogeny , 2003, Artificial Life.

[2]  Yong-Chang Jiao,et al.  MOEA/D with Uniform Design for Solving Multiobjective Knapsack Problems , 2013, J. Comput..

[3]  Wei Shih,et al.  A Branch and Bound Method for the Multiconstraint Zero-One Knapsack Problem , 1979 .

[4]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

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

[6]  P. N. Suganthan,et al.  Differential Evolution: A Survey of the State-of-the-Art , 2011, IEEE Transactions on Evolutionary Computation.

[7]  Fred Glover,et al.  Critical Event Tabu Search for Multidimensional Knapsack Problems , 1996 .

[8]  Hisao Ishibuchi,et al.  Simultaneous use of different scalarizing functions in MOEA/D , 2010, GECCO '10.

[9]  António Gaspar-Cunha,et al.  Weighted Stress Function Method for Multiobjective Evolutionary Algorithm Based on Decomposition , 2017, EMO.

[10]  Hasan Pirkul,et al.  Efficient algorithms for solving multiconstraint zero-one knapsack problems to optimality , 1985, Math. Program..

[11]  Andrzej Jaszkiewicz,et al.  On the performance of multiple-objective genetic local search on the 0/1 knapsack problem - a comparative experiment , 2002, IEEE Trans. Evol. Comput..

[12]  Kalyanmoy Deb,et al.  Multi-objective optimization using evolutionary algorithms , 2001, Wiley-Interscience series in systems and optimization.

[13]  Min Kong,et al.  A new ant colony optimization algorithm for the multidimensional Knapsack problem , 2008, Comput. Oper. Res..

[14]  Qingfu Zhang,et al.  Decomposition of a Multiobjective Optimization Problem Into a Number of Simple Multiobjective Subproblems , 2014, IEEE Transactions on Evolutionary Computation.

[15]  Masatoshi Sakawa,et al.  Genetic algorithms with double strings for 0-1 programming problems , 2003, Eur. J. Oper. Res..

[16]  David Corne,et al.  A comparison of diverse approaches to memetic multiobjective combinatorial optimization , 2000 .

[17]  Verena Heidrich-Meisner,et al.  Neuroevolution strategies for episodic reinforcement learning , 2009, J. Algorithms.

[18]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[19]  Kalyanmoy Deb,et al.  Simulated Binary Crossover for Continuous Search Space , 1995, Complex Syst..

[20]  Kiyoshi Tanaka,et al.  Local dominance and local recombination in MOEAs on 0/1 multiobjective knapsack problems , 2007, Eur. J. Oper. Res..

[21]  Janet M. Wagner,et al.  Stepwise selection of variables in data envelopment analysis: Procedures and managerial perspectives , 2007, Eur. J. Oper. Res..

[22]  Ana Maria A. C. Rocha,et al.  Improved binary artificial fish swarm algorithm for the 0-1 multidimensional knapsack problems , 2014, Swarm Evol. Comput..

[23]  G. Dantzig Discrete-Variable Extremum Problems , 1957 .

[24]  Hisao Ishibuchi,et al.  Behavior of Multiobjective Evolutionary Algorithms on Many-Objective Knapsack Problems , 2015, IEEE Transactions on Evolutionary Computation.

[25]  Franz Rothlauf,et al.  Representations for genetic and evolutionary algorithms , 2002, Studies in Fuzziness and Soft Computing.

[26]  Abdesslem Layeb,et al.  A Multi-objective Binary Cuckoo Search for Bi- criteria Knapsack Problem , 2013 .

[27]  Hisao Ishibuchi,et al.  An empirical study on similarity-based mating for evolutionary multiobjective combinatorial optimization , 2008, Eur. J. Oper. Res..

[28]  Marco Laumanns,et al.  SPEA2: Improving the strength pareto evolutionary algorithm , 2001 .

[29]  Lothar Thiele,et al.  An evolutionary algorithm for multiobjective optimization: the strength Pareto approach , 1998 .

[30]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[31]  Stéphane Bonnevay,et al.  Hybrid Metaheuristics based on MOEA/D for 0/1 multiobjective knapsack problems: A comparative study , 2012, 2012 IEEE Congress on Evolutionary Computation.

[32]  Qingfu Zhang,et al.  An Evolutionary Many-Objective Optimization Algorithm Based on Dominance and Decomposition , 2015, IEEE Transactions on Evolutionary Computation.

[33]  Hisao Ishibuchi,et al.  Diversity Improvement by Non-Geometric Binary Crossover in Evolutionary Multiobjective Optimization , 2010, IEEE Transactions on Evolutionary Computation.

[34]  Hisao Ishibuchi,et al.  Comparison Between Lamarckian and Baldwinian Repair on Multiobjective 0/1 Knapsack Problems , 2005, EMO.

[35]  Marco Laumanns,et al.  Performance assessment of multiobjective optimizers: an analysis and review , 2003, IEEE Trans. Evol. Comput..

[36]  Petersen CliffordC. A Capital Budgeting Heuristic Algorithm Using Exchange Operations , 1974 .

[37]  Kurt Spielberg,et al.  Algorithms for the Simple Plant-Location Problem with Some Side Conditions , 1969, Oper. Res..

[38]  Hiroyuki Sato,et al.  Inverted PBI in MOEA/D and its impact on the search performance on multi and many-objective optimization , 2014, GECCO.

[39]  Christine L. Mumford,et al.  Comparing representations and recombination operators for the multi-objective 0/1 knapsack problem , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[40]  Carsten Peterson,et al.  Neural Networks for Optimization Problems with Inequality Constraints: The Knapsack Problem , 1993, Neural Computation.

[41]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[42]  Hisao Ishibuchi,et al.  Effects of discrete objective functions with different granularities on the search behavior of EMO algorithms , 2012, GECCO '12.

[43]  Francisco Herrera,et al.  A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms , 2011, Swarm Evol. Comput..

[44]  Lothar Thiele,et al.  Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach , 1999, IEEE Trans. Evol. Comput..

[45]  Ralph E. Gomory,et al.  The Theory and Computation of Knapsack Functions , 1966, Oper. Res..

[46]  H. Martin Weingartner,et al.  Method for the Solution of the Multi-Dimensional 0/1 Knapsack Problem , 2015 .

[47]  Hisao Ishibuchi,et al.  Distance-Based Analysis of Crossover Operators for Many-Objective Knapsack Problems , 2014, PPSN.

[48]  Lothar Thiele,et al.  A Tutorial on the Performance Assessment of Stochastic Multiobjective Optimizers , 2006 .

[49]  Jianhua Wu,et al.  Solving 0-1 knapsack problem by a novel global harmony search algorithm , 2011, Appl. Soft Comput..

[50]  Dario Floreano,et al.  Neuroevolution: from architectures to learning , 2008, Evol. Intell..

[51]  Kate A. Smith,et al.  Neural Networks for Combinatorial Optimization: a Review of More Than a Decade of Research , 1999 .

[52]  Paolo Toth,et al.  Knapsack Problems: Algorithms and Computer Implementations , 1990 .

[53]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[54]  Andreas Drexl,et al.  A simulated annealing approach to the multiconstraint zero-one knapsack problem , 1988, Computing.

[55]  Lothar Thiele,et al.  Multiobjective Optimization Using Evolutionary Algorithms - A Comparative Case Study , 1998, PPSN.

[56]  Mohamed Naimi,et al.  The two-stage recombination operator and its application to the multiobjective 0/1 knapsack problem: A comparative study , 2009, Comput. Oper. Res..

[57]  Jiahai Wang,et al.  A Chaotic Neural Network Combined Heuristic Strategy for Multidimensional Knapsack Problem , 2008, ISICA.

[58]  Nicola Beume,et al.  SMS-EMOA: Multiobjective selection based on dominated hypervolume , 2007, Eur. J. Oper. Res..

[59]  Hisao Ishibuchi,et al.  Effects of using two neighborhood structures on the performance of cellular evolutionary algorithms for many-objective optimization , 2009, 2009 IEEE Congress on Evolutionary Computation.

[60]  José F. Fontanari,et al.  A statistical analysis of the knapsack problem , 1995 .

[61]  H. Ishibuchi,et al.  Effects of repair procedures on the performance of EMO algorithms for multiobjective 0/1 knapsack problems , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[62]  Qingfu Zhang,et al.  Multiobjective Optimization Problems With Complicated Pareto Sets, MOEA/D and NSGA-II , 2009, IEEE Transactions on Evolutionary Computation.

[63]  Eckart Zitzler,et al.  Indicator-Based Selection in Multiobjective Search , 2004, PPSN.

[64]  Akio Ogihara,et al.  Asymmetric Neural Network and Its Application to Knapsack Problem , 1995 .

[65]  Kenneth O. Stanley,et al.  A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks , 2009, Artificial Life.

[66]  Kiyoshi Tanaka,et al.  Variable space diversity, crossover and mutation in MOEA solving many-objective knapsack problems , 2012, Annals of Mathematics and Artificial Intelligence.

[67]  Carlos M. Fonseca,et al.  On the performance of linkage-tree genetic algorithms for the multidimensional knapsack problem , 2014, Neurocomputing.

[68]  Whitfield Diffie,et al.  New Directions in Cryptography , 1976, IEEE Trans. Inf. Theory.