PhD Dissertation Defense by ZHANG Ce | Document Graph Representation Learning

Much of the data on the Web can be represented in a graph structure. As a specific graph data, documents are usually connected in a graph structure. For example, Google Web pages hyperlink to other related pages, academic papers cite other papers, Facebook user profiles are connected as a social network, news articles with similar tags are linked together, etc. We call such data document graph or document network. To better make sense of the meaning within these text documents, researchers develop neural topic models. By modeling both textual content within documents and connectivity across documents, we can discover more interpretable topics to understand the corpus and better fulfill real-world applications, such as Web page searching, news article classification, academic paper indexing, and friend recommendation based on user profiles, etc. However, traditional topic models explore the content only, ignoring the connectivity. In this dissertation, we aim to develop models for document graph representation learning.

Ce Zhang is a PhD candidate in Computer Science at Singapore Management University, supervised by Prof. Hady W. Lauw. His research interests generally lie in machine learning and data mining, with a specific focus on graph representation learning, graph neural networks, and text mining. His first-authored papers are published on top venues, including NeurIPS, ICML, KDD, AAAI, CIKM, ECML/PKDD, etc. He is awarded 2021 Singapore Data Science Consortium PhD Dissertation Research Fellowship, SMU Presidential Doctoral Fellowship, and SCIS Dean's List Award. He serves as an Instructor and teaches an undergraduate core course, COR-IS1702 Computational Thinking, at SMU.