When Do GNNs Work: Understanding and Improving Neighborhood Aggregation

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering

Final Year Thesis Oral Defense

Title: "When Do GNNs Work: Understanding and Improving Neighborhood 
        Aggregation"

by

XIE Yiqing

Abstract:

Graph Neural Networks (GNNs) have been shown to be powerful in a wide 
range of graph-related tasks. While there exist various GNN models, a 
critical common ingredient is neighborhood aggregation, where the 
embedding of each node is updated by referring to the embedding of its 
neighbors. This paper aims to provide a better understanding of this 
mechanisms by asking the following question: Is neighborhood aggregation 
always necessary and beneficial? In short, the answer is no. We carve out 
two conditions under which neighborhood aggregation is not helpful: (1) 
when its neighbors are highly dissimilar and (2) when a node's embedding 
is already similar to that of its neighbors. We propose novel metrics that 
quantitatively measure these two circumstances and integrate them into an 
Adaptive-layer module. Our experiments show that allowing for 
node-specific aggregation degrees have significant advantage over current 
GNNs.


Date            : 5 May 2020 (Tueday)

Time            : 15:00 - 16:00

Zoom Meeting    : https://hkust.zoom.us/j/99695315890

Advisor         : Dr. WONG Raymond Chi-Wing

2nd Reader      : Dr. NG Wilfred Siu-Hung