Search

Session-based recommendation (SBR) aims at recommending items given the behavior sequences of anonymous users in a short-term session. Many recent SBR methods construct all sessions as a global graph that captures cross-session item transition patterns (i.e., users' global preference) to alleviate the problem of session data sparsity. However, these methods neglect that users' interests will drift as the time between the sessions constantly increases, limiting the performance improvement of SBR. To fill this gap, we divide all sessions into a group of time-slices and model the cross-session item transitions for every time-slice. We further construct two augmentation views (i.e., temporal graph and temporal hypergraph views) to model pairwise and high-order item transitions on SBR. In addition, we construct contrastive learning between two views to improve the recommendation performance by maximizing the mutual information between the item representations learned from the two views. Experiments on three public real-world datasets (i.e., Diginetica, Retailrocket, and Yoochoose) show that our model is consistently superior to the other state-of-the-art baselines, especially in time-sensitive datasets. For instance, our model achieves 14.42% and 11.72% improvements in terms of P@10 and P@20 on the Diginetica dataset, respectively. [ABSTRACT FROM AUTHOR]

Graph neural network (GNN) is considered as the state-of-art method for KG-based recommendation. However, the existing GNN-based recommendation methods incorporating KG information fail to fully consider interactions between nodes in the process of message passing and aggregating, which will affect the performance improvement of recommendation. To resolve the above limitation, we propose a Feature Interactive Graph Neural Network for KG-based Recommendation (FIKGRec) to explicitly model sophisticated feature interactions from the complex structure of heterogeneous knowledge graph. The overall framework consists of three components: (1) For items, we construct item-KGs where the nodes (entities) denote items and items' features, and edges represent the relations between entities. Modeling feature interaction can be thus transformed into modeling node (entity) interaction on the knowledge graph. Specifically, we integrate the collaborative signals into the process of KG signals propagation to capture more precise user preferences and then employ the feature entity interaction layer to incorporate the interaction information between entities in the process of neighbor aggregation of entities in item-KG. (2) For users, a preference-aware attention mechanism is designed to obtain the user's fine-grained preference for items that have been interacted. (3) The final representations of users and items are fed to deep neural network (DNN) to model complex correlations between them. Extensive experiments on three real-world datasets demonstrate the better performance of our FIKGRec framework compared to state-of-the-arts methods. • Graph Neural Network technic is used to explore knowledge graph. • Collaborative signals are integrated into the process of KG signals propagation. • Node (entity) interaction is considered when information aggregation. • A preference-aware attention mechanism is proposed for user-end modeling. [ABSTRACT FROM AUTHOR]