How to get meta-path for IMDB dataset?

seongjunyun / Graph_Transformer_Networks

Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)

960 stars 179 forks source link

How to get meta-path for IMDB dataset? #23

Closed ZHANG-GuiGui closed 4 years ago

ZHANG-GuiGui commented 4 years ago

Hi, I've noticed that you use main.py for DBLP and ACM dataset, but main_sparse.py for IMDB dataset. For main.py, the weight W or the list Ws is updated every epoch. But for main_sparse.py, the weight is unchanged for every epoch. It is always 0.2. So how you derived that the IMDB meta-path learned by GTN?

ZHANG-GuiGui commented 4 years ago

Sorry, I found that this has already been answered here and here

Notice that torch-sparse == 0.4.4 and torch-geometric == 1.4.2