microsoft/FOST

gconv.py

yinxc opened this issue · 1 comments

yinxc commented

Are there any papers to describe principles of the sentence 'Build an edge-attribute-aware graph convolutional layer' in class EGNNConv?

Most papers of spatial-temporal forecasting have utilized edge features (weights). This implementation of EGNNConv is adapted from our practice, which does not directly connect to specific papers.