Generative Adversarial Network Based Service Recommendation in Heterogeneous Information Networks

Service recommendation is widely used to locate developers' desired services. Previous methods mainly focus on employing collaborative filtering (CF) techniques to recommend services to developers. However, these methods have some problems, such as being sensitive to sparse data and having limited predictive ability to new developers. Generative adversarial network (GAN) can solve the above mentioned problems, since it can learn the data distribution from a limited amount of data and generate a new developer's preference score for a service, even if he/she has not invoked the service. In this paper, we propose a novel GAN based service recommendation method. It first constructs a heterogeneous information network (HIN) by utilizing mashup information, service information and their respective attribute information. Then, it samples meta-paths of different semantic relationships and constructs similarity matrices between mashups and services through meta-paths based similarity measurement. Finally, by leveraging the adversarial training between the discriminator and the generator, the discriminator can effectively guide the generator to generate a preference vector for the developer, thus recommending a list of services for him/her according to his/her given mashup attribute information. Comprehensive experimental results on a real-world dataset demonstrate the superiority of the proposed method.