AI Open (Jan 2022)
A survey on heterogeneous information network based recommender systems: Concepts, methods, applications and resources
Abstract
As an important way to alleviate information overload, a recommender system aims to filter out irrelevant information for users and provides them items that they may be interested in. In recent years, an increasing amount of works have been proposed to introduce auxiliary information in recommender systems to alleviate data sparsity and cold-start problems. Among them, heterogeneous information networks (HIN)-based recommender systems provide a unified approach to fuse various auxiliary information, which can be combined with mainstream recommendation algorithms to effectively enhance the performance and interpretability of models, and thus have been applied in many kinds of recommendation tasks. This paper provides a comprehensive and systematic survey of HIN-based recommender systems, including four aspects: concepts, methods, applications, and resources. Specifically, we firstly introduce the concepts related to recommender systems, heterogeneous information networks and HIN-based recommendation. Secondly, we present more than 70 methods categorized according to models or application scenarios, and describe representative methods symbolically. Thirdly, we summarize the benchmark datasets and open source code. Finally, we discuss several potential research directions and conclude our survey.
