Efficient and Scalable Training of Graph Neural Networks: A Literature Review

The Hong Kong University of Science and Technology (Guangzhou)

Data Science and Analytics Thrust

PhD Qualifying Examination

By Mr. ZHANG, Xin

Abstract

Graph Neural Networks are popular these days due to their strong capability in modeling and predicting complex graph-structured data. However, real-world graphs are usually giant in nature, containing millions of nodes and billions of edges. Efficient training of GNNs on such giant graphs is a challenge. Recently, many research studies have been done that propose efficient and scalable solutions from different perspectives to address the challenge. The survey provides a structured review of these existing works, classifying them based on their position in the GNN training stack. This work also details current PhD progress as well as a general outline for the future.

PQE Committee

Chair of Committee: Prof. YI, Ke

Prime Supervisor: Prof. CHEN, Lei

Co-Supervisor: Prof. LUO, Qiong

Examiner: Prof. WANG, Wenjia