Zexi Huang successfully passed his Phd proposal on the topic "Learning Representations for Information-rich Graphs".

Committee: Ambuj Singh (Chair), Yu-Xiang Wang, Noah Friedkin, Xifeng Yan

Graphs are a ubiquitous data structure for encoding rich relational information in various domains, be it social networks, recommender systems, protein-protein interactions, and many others. Recent advances in graph representation learning have led to new state-of-the-art results in various graph-related tasks, such as link prediction, community detection, and graph classification. In this talk, I will start with an overview of my research in learning representation for information-rich graphs. The rest of the talk will cover my studies in three subareas: (1) representation learning for multiscale graphs, and its applications in link prediction, community detection, and anomaly detection; (2) representation learning for signed graphs, and its applications in signed link prediction and characterizing social polarization; and (3) representation learning for attributed graphs, and its applications in node classification, link prediction, and counterfactual explanation.