AI open2022 ｜ overview of recommendation systems based on heterogeneous information networks: concepts, methods, applications and resources

subject ：A survey on heterogeneous information network based recommender systems: Concepts, methods, applications and resources

Periodical ：AI Open 2022

Thesis link ：https://www.sciencedirect.com/science/article/pii/S2666651022000092/

As an important means to alleviate information overload , The recommendation system is designed to filter out irrelevant information for users , And provide them with projects they may be interested in . In recent years , More and more work has proposed introducing auxiliary information into recommendation systems to alleviate the problems of data sparsity and cold start . among , Based on heterogeneous information network (HIN) The recommendation system of provides a unified method of fusing various auxiliary information , It can be combined with mainstream recommendation algorithms , Effectively improve the performance and interpretability of the model , Thus, it can be applied to a variety of recommendation tasks . This article from the concept 、 Method 、 Application and resources are based on HIN A comprehensive and systematic overview of the recommendation system .

This article is organized as follows ：

• In chapter two , We introduce the related concepts and definitions of recommendation system and heterogeneous information network .
• In chapter three , According to different models, we compare the results based on HIN The recommendation system is classified , The existing recommendation methods are systematically analyzed .
• In chapter four , Based on different application scenarios HIN The recommendation system is classified , And discuss the characteristics of each scene .
• In chapter five , We introduced some commonly used data sets , And summarizes some applications based on HIN Open source tools for recommendation systems .
• In chapter six , Prospect based on HIN The future research direction of recommendation system .
• In Chapter 7 , We reviewed and summarized our review .