Reviewing Developments of Graph Convolutional Network Techniques for Recommendation Systems
This is a review paper, so it is incremental by nature, summarizing existing developments rather than introducing new methods.
The paper reviews recent literature on graph neural network-based recommender systems, categorizing them by settings and models, and analyzes challenges in graph construction, embedding propagation, and computation efficiency.
The Recommender system is a vital information service on today's Internet. Recently, graph neural networks have emerged as the leading approach for recommender systems. We try to review recent literature on graph neural network-based recommender systems, covering the background and development of both recommender systems and graph neural networks. Then categorizing recommender systems by their settings and graph neural networks by spectral and spatial models, we explore the motivation behind incorporating graph neural networks into recommender systems. We also analyze challenges and open problems in graph construction, embedding propagation and aggregation, and computation efficiency. This guides us to better explore the future directions and developments in this domain.