Most sequential recommendation models capture the features of consecutive items in a user-item interaction history. Though effective, their representation expressiveness is still hindered by the sparse learning signals. As a result, the sequential recommender is prone to make inconsistent predictions. In this paper, we propose a model, SSI, to improve sequential recommendation consistency with Self-Supervised Imitation. Precisely, we extract the consistency knowledge by utilizing three self-supervised pre-training tasks, where temporal consistency and persona consistency capture user-interaction dynamics in terms of the chronological order and persona sensitivities, respectively. Furthermore, to provide the model with a global perspective, global session consistency is introduced by maximizing the mutual information among global and local interaction sequences. Finally, to comprehensively take advantage of all three independent aspects of consistency-enhanced knowledge, we establish an integrated imitation learning framework. The consistency knowledge is effectively internalized and transferred to the student model by imitating the conventional prediction logit as well as the consistency-enhanced item representations. In addition, the flexible self-supervised imitation framework can also benefit other student recommenders. Experiments on four real-world datasets show that SSI effectively outperforms the state-of-the-art sequential recommendation methods.

Sequential recommendation (SR) has attracted much research attention in the past few years. Most existing attribute integrated SR models do not directly model the complex relations between items and categorical attributes, as well do not exploit the power of attribute sequence in predicting the next item. In this paper, we propose an Item Categorical Attribute Integrated Sequential Recommendation (ICAI-SR) framework, which consists of an Item-Attribute Aggregation (IAA) model and Entity Sequential (ES) models. In IAA model, we employ a heterogeneous graph to represent the complex relations between items and different types of categorical attributes, then the attention mechanism based neighborhood aggregation is designed to model the correlations between items and attributes. For ES models, there are one Item Sequential (IS) model and one or more Attribute Sequential (AS) models. With IS and AS models, not only the item sequence but also the attribute sequence are used to predict the next item during model training. ICAI-SR is instantiated by taking Gated Recurrent Unit (GRU) and Bidirectional Encoder Representations from Transformers (BERT) as ES models, resulting in ICAI-GRU and ICAI-BERT respectively. Extensive experiments have been conducted on three public datasets to validate the performance of ICAI-SR. Experimental Results show that ICAI-SR performs better than both basic SR models and a competitive attribute integrated SR model.