Graph Data Mining in Recommender Systems

With the rapid development of e-commerce, massive data is generated from various e-commerce platforms. Most of the generated data can be represented in the forms of graph, which is capable to demonstrate the complicated relations among various entities, for example, graphs describe the interactions history between users and items. It is critical for the platforms to mine graph data to formulate recommendation strategy to gain more profits. For instance, in a user-item interaction graph, we can utilize graph data mining techniques to capture users’ behavioral patterns to make personalized recommendation strategies. Graph data mining in recommendation is currently a research topic attracts more and more attentions from industry and academic fields. In this half-day tutorial, we will present some key graph data mining methods and its applications in recommendation. We hope to find out the directions for the future work and that more theoretical models can be applied under real-world scenarios.