DEKGCI: A double-sided recommendation model for integrating knowledge graph and user-item interaction graph

TL;DR

DEKGCI is a novel recommendation model that effectively integrates high-order information from both knowledge graphs and user-item interaction graphs to improve user and item representations, leading to better recommendation accuracy.

Contribution

The paper introduces DEKGCI, a double-sided recommendation model that jointly utilizes high-order signals from knowledge and interaction graphs, which was underexplored in prior work.

Findings

DEKGCI outperforms seven state-of-the-art baselines in AUC and ACC.

High-order information integration enhances recommendation performance.

Experimental results validate the effectiveness of the proposed model.

Abstract

Both knowledge graphs and user-item interaction graphs are frequently used in recommender systems due to their ability to provide rich information for modeling users and items. However, existing studies often focused on one of these sources (either the knowledge graph or the user-item interaction graph), resulting in underutilization of the benefits that can be obtained by integrating both sources of information. In this paper, we propose DEKGCI, a novel double-sided recommendation model. In DEKGCI, we use the high-order collaborative signals from the user-item interaction graph to enrich the user representations on the user side. Additionally, we utilize the high-order structural and semantic information from the knowledge graph to enrich the item representations on the item side. DEKGCI simultaneously learns the user and item representations to effectively capture the joint interactions between users and items. Three real-world datasets are adopted in the experiments to evaluate DEKGCI's performance, and experimental results demonstrate its high effectiveness compared to seven state-of-the-art baselines in terms of AUC and ACC.