Representation learning for graph neural networks
Project Description

Generalizable, transferrable, and robust representation learning on graph-structured
data remains a challenge for current graph neural networks (GNNs). Unlike what
has been developed for convolutional neural networks (CNNs) for image data,
self-supervised learning and pre-training are less explored for GNNs.

Supervisor
LI Xiaomeng
Quota
3
Course type
UROP1000
UROP1100
UROP2100
UROP3100
UROP4100
Applicant's Roles

The applicant will run related code, discuss the ideas with a senior Ph.D. and advisor.

Applicant's Learning Objectives

1, the applicant will get familiar with GCN and contrastive learning.
2, write a high-quality paper if possible.

Complexity of the project
Easy