Knowledge graph-based recommendation system enhanced by neural collaborative filtering and knowledge graph embedding

Abstract

Recommendation systems are an important and undeniable part of modern systems and applications. Recommending items and users to the users that are likely to buy or interact with them is a modern solution for AI-based applications. In this article, a novel architecture is used with the utilization of pre-trained knowledge graph embeddings of different approaches. The proposed architecture consists of several stages that have various advantages. In the first step of the proposed method, a knowledge graph from data is created, since multi-hop neighbors in this graph address the ambiguity and redundancy problems. Then knowledge graph representation learning techniques are used to learn low-dimensional vector representations for knowledge graph components. In the following a neural collaborative filtering framework is used which benefits from no extra weights on layers. It is only dependent on matrix operations. Learning over these operations uses the pre-trained embeddings, and fine-tune them. Evaluation metrics show that the proposed method is superior in over other state-of-the-art approaches. According to the experimental results, the criteria of recall, precision, and F1-score have been improved, on average by 3.87%, 2.42%, and 6.05%, respectively.