Spatio-Temporal Graph Convolutional Networks: Spatial Layers First or Temporal Layers First?

MPhil Thesis Defence


Title: "Spatio-Temporal Graph Convolutional Networks: Spatial Layers First 
or Temporal Layers First?"

By

Mr. Yuen Hoi LAU


Abstract

Traffic forecasting is an important and challenging problem for 
intelligent transportation systems due to the complex spatial dependencies 
among neighboring roads and changing road conditions in different time 
periods. Spatio-temporal graph convolutional networks (STGCNs) are usually 
adopted to forecast traffic features in a road network. Existing STGCN 
models involve spatial layers and temporal layers. Some models involve 
spatial layers first and then temporal layers and some other models 
involves these layers in a reverse order. This creates an interesting 
research question on whether the ordering of involving the spatial layers 
(or temporal layers) first in an existing STGCN model could improve the 
prediction performance. To the best of our knowledge, we are the first to 
study this interesting research problem, which creates a deep insight as a 
guideline to the research community on how to design STGCN models.

Extensive experiments were conducted to study a number of representative 
STGCN models for this research problem. The findings are that these models 
with spatial layers constructed before temporal layers has a higher chance 
to outperform that with temporal layers constructed first, which suggests 
the future design principle of STGCN models.


Date:  			Thursday, 19 August 2021

Time:			10:00am - 12:00noon

Zoom meeting:
https://hkust.zoom.us/j/95636242649?pwd=K3pTUjlWMGx1VTBxSlJZaTdLYzlOUT09

Committee Members:	Prof. Raymond Wong (Supervisor)
 			Prof. Nevin Zhang (Chairperson)
 			Dr. Yangqiu Song


**** ALL are Welcome ****