Learning Graph ODE for Continuous-Time Sequential Recommendation

Sequential recommendation aims at understanding user preference by capturing successive behavior correlations, which are usually represented as the item purchasing sequences based on their past interactions. Existing efforts generally predict the next item via modeling the sequential patterns. Despite effectiveness, there exist two natural deficiencies: (i) user preference is dynamic in nature, and the evolution of collaborative signals is often ignored; and (ii) the observed interactions are often irregularly-sampled, while existing methods model item transitions assuming uniform intervals. Thus, how to effectively model and predict the underlying dynamics for user preference becomes a critical research problem. To tackle the above challenges, in this paper, we focus on continuous-time sequential recommendation and propose a principled graph ordinary differential equation framework named GDERec. Technically, GDERec is characterized by an autoregressive graph ordinary differential equation consisting of two components, which are parameterized by two tailored graph neural networks (GNNs) respectively to capture user preference from the perspective of hybrid dynamical systems. On the one hand, we introduce a novel ordinary differential equation based GNN to implicitly model the temporal evolution of the user-item interaction graph. On the other hand, an attention-based GNN is proposed to explicitly incorporate collaborative attention to interaction signals when the interaction graph evolves over time. The two customized GNNs are trained alternately in an autoregressive manner to track the evolution of the underlying system from irregular observations, and thus learn effective representations of users and items beneficial to the sequential recommendation. Extensive experiments on five benchmark datasets demonstrate the superiority of our model over various state-of-the-art recommendation methods.

I. Introduction

Recommender systems, as critical components to alleviate information overloading, have attracted significant attention for users to discover items of interest in various online applications such as e-commerce [1], [2], [3] and social media platforms [4], [5], [6]. The key of a successful recommender system lies in accurately predicting users’ interests toward items based on their historical interactions. Traditional recommendation methods such as matrix factorization [7], [8], [9] usually hold the assumption of independence between different user behaviors. However, user preference is typically dynamically embedded in item transitions and sequence patterns, and successive behaviors can be highly correlated. One promising direction to effectively achieve this goal is the sequential recommendation (SR), which aims at explicitly modeling the correlations between successive user behaviors. The success of SR in the past few years have significantly enhanced user experience in both search efficiency and new product discovery.