Open AccessRecommendation System Based on Generative Adversarial Network with Graph Convolutional Layers
Author(s) -
Takato Sasagawa,
Shichio Kawai,
Hajime Nobuhara
Publication year - 2021
Publication title -
journal of advanced computational intelligence and intelligent informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.172
H-Index - 20
eISSN - 1343-0130
pISSN - 1883-8014
DOI - 10.20965/jaciii.2021.p0389
Subject(s) - movielens , computer science , scalability , graph , generative adversarial network , recommender system , bipartite graph , convolution (computer science) , theoretical computer science , generative grammar , adversarial system , artificial intelligence , domain (mathematical analysis) , field (mathematics) , node (physics) , latent dirichlet allocation , machine learning , data mining , deep learning , collaborative filtering , topic model , database , mathematics , artificial neural network , pure mathematics , mathematical analysis , structural engineering , engineering
A graph convolutional generative adversarial network (GCGAN) is proposed to provide recommendations for new users or items. To maintain scalability, the discriminator was improved to capture the latent features of users and items, using graph convolution from a minibatch-sized bipartite graph. In the experiment using MovieLens, it was confirmed that the proposed GCGAN had better performance than the conventional CFGAN, when MovieLens 1M was employed with sufficient data. The proposed method is characterized in such a manner that it can learn domain information of both, users and items, and it does not require to relearn a model for a new node. Further, it can be developed for any service having such conditions, in the information recommendation field.