Graph Neural Networks with Dynamic and Static Representations for Social Recommendation

TL;DR

This paper introduces GNN-DSR, a graph neural network model that captures both dynamic and static user and item representations, along with social and item correlations, to improve social recommendation accuracy.

Contribution

It proposes a novel GNN framework that models both short-term dynamic and long-term static interests of users and items, incorporating social influence and item correlations.

Findings

GNN-DSR outperforms baseline models on three real-world datasets.

Incorporating dynamic and static representations improves recommendation accuracy.

Attention mechanisms effectively capture social and item influence.

Abstract

Recommender systems based on graph neural networks receive increasing research interest due to their excellent ability to learn a variety of side information including social networks. However, previous works usually focus on modeling users, not much attention is paid to items. Moreover, the possible changes in the attraction of items over time, which is like the dynamic interest of users are rarely considered, and neither do the correlations among items. To overcome these limitations, this paper proposes graph neural networks with dynamic and static representations for social recommendation (GNN-DSR), which considers both dynamic and static representations of users and items and incorporates their relational influence. GNN-DSR models the short-term dynamic and long-term static interactional representations of the user's interest and the item's attraction, respectively. Furthermore, the attention mechanism is used to aggregate the social influence of users on the target user and the correlative items' influence on a given item. The final latent factors of user and item are combined to make a prediction. Experiments on three real-world recommender system datasets validate the effectiveness of GNN-DSR.