Recommender　systems　play　an　important　role　in　the　age　of　mass　information.　They　allow　users　to　discover　items　that　match　their　tastes.　In　this　paper,　we　propose　a　novel　method,　called　adversarial　variational　autoencoder,　for　top-N　recommendation.　We　use　generative　adversarial　networks　to　regularize　variational　autoencoder　by　imposing　an　arbitrary　prior　on　the　latent　representation　of　VAE,　which　makes　the　recommendation　model.　We　define　a　joint　objective　function　as　a　minimization　problem.　Our　experiments　on　three　datasets　show　that　the　proposed　model　achieves　high　recommendation　accuracy　compared　to　other　state-of-the-art　models.　©　2018　IEEE.