Ripple Knowledge Graph Convolutional Networks For Recommendation Systems

TL;DR

This paper presents RKGCN, a novel knowledge graph convolutional network that enhances recommendation systems by integrating user and item knowledge graphs, leading to more personalized and accurate recommendations.

Contribution

The paper introduces RKGCN, an end-to-end deep learning model that dynamically analyzes user preferences and combines knowledge graphs for improved recommendation accuracy.

Findings

RKGCN outperforms 5 baseline models on three real-world datasets.

The model improves recommendation relevance and personalization.

Experimental results demonstrate superior effectiveness across multiple domains.

Abstract

Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy. This paper introduces an end-to-end deep learning model, named RKGCN, which dynamically analyses each user's preferences and makes a recommendation of suitable items. It combines knowledge graphs on both the item side and user side to enrich their representations to maximize the utilization of the abundant information in knowledge graphs. RKGCN is able to offer more personalized and relevant recommendations in three different scenarios. The experimental results show the superior effectiveness of our model over 5 baseline models on three real-world datasets including movies, books, and music.