Abstract Non-IID recommender system discloses the nature of recommendation and has shown its potential in improving recommendation quality and addressing issues such as sparsity and cold start. It leverages existing work that usually treats users/items as independent while ignoring the rich couplings within and between users and items, leading to limited performance improvement. In reality, users/items are related with various couplings existing within and between users and items, which may better explain how and why a user has personalized preference on an item. This work builds on nonIID learning to propose a neural user-item coupling learning for collaborative filtering, called CoupledCF. CoupledCF jointly learns explicit and implicit couplings within/between users and items w.r.t. user/item attributes and deep features for deep CF recommendation. Empirical results on two real-world large datasets show that CoupledCF significantly outperforms two latest neural recommenders: neural matrix factorization and Google’s Wide&Deep network.