With rapid evolution of e-commerce, it is essential but challenging to quickly provide a recommending service for users. The recommender system can be divided into two stages: retrieval and ranking. However, most recent academic research has focused on the second stage for datasets with limited size, while the role of retrieval is heavily underestimated. Generally, graph-based or sequential models are used to generate item embedding for the retrieval task. However, the graph-based methods suffer from over-smoothing, while sequential models are largely influenced by data sparseness. To alleviate these issues, we propose NATM—a novel embedding-based method in large-scale learning incorporating both graph-based and sequential information. NATM consists of two key components: i) neighbor augmented graph construction with user behaviors to enhance item embedding and mitigate data sparseness, followed by ii) transformer-based representation network, targeting on minimizing NCE loss. The competitive performance of the proposed method is demonstrated through comprehensive experiments, including a benchmark study on MovieLens dataset and a real-world e-commerce scenario in Alibaba Group.