A SURVEY ON DYNAMIC GRAPH NEURAL NETWORKS

PhD Qualifying Examination


Title: "A SURVEY ON DYNAMIC GRAPH NEURAL NETWORKS"

by

Mr. Yiming LI


Abstract:

Dynamic graphs serve as the foundation of applications in various fields such
as social network analysis, recommender systems, and epidemiology. By
representing complex graphs as structures that change over time, dynamic graph
models can leverage both structural and temporal patterns. However, navigating
the dynamic graph literature is challenging due to its origins in diverse
fields and the inconsistent terminology used. In recent years, graph neural
networks (GNNs) have gained significant attention for their impressive
performance in downstream tasks, including link prediction and node
classification. Despite the popularity of graph neural networks and the proven
benefits of dynamic graph models, little focus has been given to graph neural
networks specifically designed for dynamic graphs. In this survey, we aim to
clarify the concepts of dynamic graphs, present a thorough review of existing
dynamic graph neural networks (DGNNs), and provide an insightful discussion on
potential future research directions in enhancing the representation learning
on dynamic graphs.


Date:                   Friday, 28 July 2023

Time:                   10:00am - 12:00noon

Venue:                  Room 5501
                        Lifts 25/26

Committee Members:      Prof. Lei Chen (Supervisor)
                        Prof. Raymond Wong (Chairperson)
                        Dr. Minhao Cheng
                        Dr. Shuai Wang


**** ALL are Welcome ****