Recent Advances in Heterogeneous Relation Learning for Recommendation

TL;DR

This survey reviews recent developments in heterogeneous relational learning for recommendation systems, focusing on methods that incorporate diverse dependencies among users and items to improve personalization.

Contribution

It categorizes and analyzes recent research approaches like social recommendation, knowledge graphs, and multi-behavior models, highlighting their techniques and future directions.

Findings

Heterogeneous relational learning enhances recommendation accuracy.

Graph neural networks effectively model complex user-item dependencies.

Future research opportunities include integrating more diverse data sources.

Abstract

Recommender systems have played a critical role in many web applications to meet user's personalized interests and alleviate the information overload. In this survey, we review the development of recommendation frameworks with the focus on heterogeneous relational learning, which consists of different types of dependencies among users and items. The objective of this task is to map heterogeneous relational data into latent representation space, such that the structural and relational properties from both user and item domain can be well preserved. To address this problem, recent research developments can fall into three major lines: social recommendation, knowledge graph-enhanced recommender system, and multi-behavior recommendation. We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information. Finally, we present an exploratory outlook to highlight several promising directions and opportunities in heterogeneous relational learning frameworks for recommendation.