Learning Graph ODE for Continuous-Time Sequential Recommendation
arXiv:2304.07042 · doi:10.1109/TKDE.2024.3349397
Abstract
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. 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.
arXiv commentAccepted by EEE Transactions on Knowledge and Data Engineering (TKDE 2024)
References in corpus (18)
- BPR: Bayesian Personalized Ranking from Implicit Feedback
- Neural Graph Collaborative Filtering
- Session-based Recommendation with Graph Neural Networks
- Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting
- Disentangled Graph Collaborative Filtering
- Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks
- Session-based Social Recommendation via Dynamic Graph Attention Networks
- A Comprehensive Survey on Deep Graph Representation Learning
- Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors
- Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
- Debiased Contrastive Learning for Sequential Recommendation
- Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation
- GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
- STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction
- DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
- A Diffusion model for POI recommendation
- Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation
- OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision