Social Recommendation through Heterogeneous Graph Modeling of the Long-term and Short-term Preference Defined by Dynamic Time Spans

TL;DR

This paper introduces a novel heterogeneous graph model for social recommendation that captures users' long-term and short-term preferences over time without complex dynamic graphs, showing superior performance on real data.

Contribution

It proposes a new method that incorporates dynamic social network properties into a static heterogeneous graph using period nodes and edge weights.

Findings

Model outperforms existing methods on real-world data

Effective in capturing user preferences over different time spans

Demonstrates the importance of modeling temporal dynamics in social recommendation

Abstract

Social recommendations have been widely adopted in substantial domains. Recently, graph neural networks (GNN) have been employed in recommender systems due to their success in graph representation learning. However, dealing with the dynamic property of social network data is a challenge. This research presents a novel method that provides social recommendations by incorporating the dynamic property of social network data in a heterogeneous graph. The model aims to capture user preference over time without going through the complexities of a dynamic graph by adding period nodes to define users' long-term and short-term preferences and aggregating assigned edge weights. The model is applied to real-world data to argue its superior performance. Promising results demonstrate the effectiveness of this model.