Abstract

Graph is an expressive and powerful data structure that is widely applicable, due to its flexibility and effectiveness in modeling and representing graph structure data. It has been more and more popular in various fields, including biology, finance, transportation, social network, among many others. Recommender system, one of the most successful commercial applications of the artificial intelligence, whose user-item interactions can naturally fit into graph structure data, also receives much attention in applying graph neural networks (GNNs). We first summarize the most recent advancements of GNNs, especially in the recommender systems. Then we share our two case studies, dynamic GNN learning and device-cloud collaborative Learning for GNNs.We finalize with discussions regarding the future directions of GNNs in practice.

Contents

• GNN for Recommender System in Practice
• Introduction of Graph Neural Networks
• Introduction of Modern Recommender System
• Classic Approaches to Predict User-Item Preference
• Item Recommendation in user-item Recommender Systems: a Bipartite Graph Perspective
• Case Study: Dynamic GNN Learning
• Dynamic Sequential Graph
• DSGL: Dynamic Sequential Graph Learning
• Model Prediction
• Experiments and Disucssion
• Case Study: Device-Cloud Collaborative Learning for GNNs
• The proposed framework
• Experiments and Discussions
• Future Directions

Citation