Recommending on graphs: a comprehensive review from a data perspective

TL;DR

This paper provides a comprehensive survey of graph learning-based recommender systems, categorizing graph types, analyzing frameworks, and discussing challenges and future research directions from a data perspective.

Contribution

It systematically categorizes graph types in GLRSs, analyzes their characteristics, and discusses state-of-the-art frameworks and challenges in the field.

Findings

Various graph types are categorized and analyzed for their properties.

State-of-the-art frameworks address challenges like scalability and fairness.

Future research directions are proposed for the rapidly growing area.

Abstract

Recent advances in graph-based learning approaches have demonstrated their effectiveness in modelling users' preferences and items' characteristics for Recommender Systems (RSS). Most of the data in RSS can be organized into graphs where various objects (e.g., users, items, and attributes) are explicitly or implicitly connected and influence each other via various relations. Such a graph-based organization brings benefits to exploiting potential properties in graph learning (e.g., random walk and network embedding) techniques to enrich the representations of the user and item nodes, which is an essential factor for successful recommendations. In this paper, we provide a comprehensive survey of Graph Learning-based Recommender Systems (GLRSs). Specifically, we start from a data-driven perspective to systematically categorize various graphs in GLRSs and analyze their characteristics. Then, we discuss the state-of-the-art frameworks with a focus on the graph learning module and how they address practical recommendation challenges such as scalability, fairness, diversity, explainability and so on. Finally, we share some potential research directions in this rapidly growing area.