URIR: Recommendation algorithm of user RNN encoder and item encoder based on knowledge graph

TL;DR

This paper introduces URIR, a recommendation algorithm that leverages knowledge graphs with user RNN encoders and item encoders to improve recommendation accuracy, demonstrating superior performance on real-world datasets.

Contribution

The paper proposes a novel URIR algorithm that encodes users and items using RNNs and knowledge graph information, enhancing recommendation quality over existing methods.

Findings

URIR outperforms state-of-the-art algorithms in AUC, Precision, Recall, and MRR.

Encoding items with high-level neighbor information improves representation quality.

Using knowledge graphs effectively enhances user and item coding for recommendations.

Abstract

Due to a large amount of information, it is difficult for users to find what they are interested in among the many choices. In order to improve users' experience, recommendation systems have been widely used in music recommendations, movie recommendations, online shopping, and other scenarios. Recently, Knowledge Graph (KG) has been proven to be an effective tool to improve the performance of recommendation systems. However, a huge challenge in applying knowledge graphs for recommendation is how to use knowledge graphs to obtain better user codes and item codes. In response to this problem, this research proposes a user Recurrent Neural Network (RNN) encoder and item encoder recommendation algorithm based on Knowledge Graph (URIR). This study encodes items by capturing high-level neighbor information to generate items' representation vectors and applies an RNN and items' representation vectors to encode users to generate users' representation vectors, and then perform inner product operation on users' representation vectors and items' representation vectors to get probabilities of users interaction with items. Numerical experiments on three real-world datasets demonstrate that URIR is superior performance to state-of-the-art algorithms in indicators such as AUC, Precision, Recall, and MRR. This implies that URIR can effectively use knowledge graph to obtain better user codes and item codes, thereby obtaining better recommendation results.