Fairness in Graph-based Recommendation: Methods Overview

The development of neural networks and machine learning methods has contributed to the widespread popularity of recommender systems, especially those based on graphs. Recommender systems are integral components of systems that often make decisions based on human factors. Therefore, it is not surprising that the development of such systems frequently leads to problems rooted in human nature, such as discrimination, bias, and inequality, among others. One such issue is fairness. Pairing graph-based recommender systems with the fairness problem has led to the development of methods and algorithms aimed at addressing fairness concerns. This paper provides an overview of some of the more significant methods recently developed, their applications, and the results obtained when applied to specific datasets. The methods and algorithms discussed are based on machine learning, specifically neural network methods. Additionally, this paper aims to demonstrate the importance of fair recommendations and highlight the potential for further action in this area.