Abstract Latent factor models have been widely used for recommendation. Most existing latent factor models mainly utilize the rating information between users and items, although some recently extended models add some auxiliary information to learn a uni?ed latent factor between users and items. The uni?ed latent factor only represents the latent features of users and items from the aspect of purchase history. However, the latent features of users and items may stem from different aspects, e.g., the brandaspect and category-aspect of items. In this paper, we propose a Neural network based Aspect-level Collaborative Filtering model (NeuACF) to exploit different aspect latent factors. Through modelling rich objects and relations in recommender system as a heterogeneous information network, NeuACF ?rst extracts different aspect-level similarity matrices of users and items through different meta-paths and then feeds an elaborately designed deep neural network with these matrices to learn aspect-level latent factors. Finally, the aspect-level latent factors are effectively fused with an attention mechanism for the top-N recommendation. Extensive experiments on three real datasets show that NeuACF signi?cantly outperforms both existing latent factor models and recent neural network models.