Introduction to the Special Section on Graph Technologies for User Modeling and Recommendation, Part 2

As a powerful data structure that represents the relationships among data objects, graph-structure data is ubiquitous in real-world applications. Learning on graph-structure data has become a hot spot in machine learning and data mining. Since most data in user-oriented services can be naturally organized as graphs, graph technologies have attracted increasing attention from IR community and achieved immense success, especially in two major research topics—user modeling and recommendation. In the recent decade, the IR and related communities have witnessed a number of major contributions to the field of graph learning. They include but not limited to collaborative filtering (e.g., He et al. [2020], Wang et al. [2019b], Wu et al. [2021], and Ying et al. [2018]), knowledge-aware recommendation (e.g., Cao et al. [2019] andWang et al. [2018, 2019a]), user profiling and demographic inference (e.g., Chen et al. [2019] and Rahimi et al. [2018]), social and sequential recommendation (e.g., Wang et al. [2020b] and Wu et al. [2019a, b]), bias and fairness (e.g., Rahman et al. [2019], Zhang et al. [2021a], and Zheng et al. [2021]). The growing body of work in this area has been supplemented by an increasing number of recent workshops (e.g., Cui et al. [2021], Ding et al. [2020], Jannach et al. [2020], and Yin et al. [2021]) and tutorials (e.g., Chen et al. [2020], Mehrotra et al. [2020], Tang and Dong [2019], Wang et al. [2020a], and Xu et al. [2018]). Despite such great