Multi-objective Combinatorial Generative Adversarial Optimization and Its Application in Crowdsensing

Abstract

With the increasing of the decision variables in multi-objective combinatorial optimization problems, the traditional evolutionary algorithms perform worse due to the low efficiency for generating the offspring by a stochastic mechanism. To address the issue, a multi-objective combinatorial generative adversarial optimization method is proposed to make the algorithm capable of learning the implicit information embodied in the evolution process. After classifying the optimal non-dominated solutions in the current generation as real data, the generative adversarial network (GAN) is trained by them, with the purpose of learning their distribution information. The Adam algorithm that employs the adaptively learning rate for each parameter is introduced to update the main parameters of GAN. Following that, an offspring reproduction strategy is designed to form a new feasible solution from the decimal output of the generator. To further verify the rationality of the proposed method, it is applied to solve the participant selection problem of the crowdsensing and the detailed offspring reproduction strategy is given. The experimental results for the crowdsensing systems with various tasks and participants show that the proposed algorithm outperforms the others in both convergence and distribution.

The application of evolutionary computation in generative adversarial networks (GANs): a systematic literature survey

“…20. Guo et al (2020) proposed a multi-objective combinatorial generative adversarial optimization algorithm (MOCGAO) based on GAO, which combined generative adversarial optimization with NSGAII. The initialization is to select the optimal value of the randomly generated individuals by the greedy strategy, identify the optimal non-dominated solutions of the current generation by the classification strategy and use them as real data to train GANs.…”