search

JD-AI-Research-Silicon-Valley / SACN

End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
MIT License
113 stars 30 forks source link

A question about the WGCN in your paper #11

Closed jianyucai closed 4 years ago

jianyucai commented 4 years ago

Hi, thanks for your code, I have a question about the WGCN in your paper.

The WGCN implemented in your code seems different from the traditional GCN. Traditional GCN uses the Symmetric normalized Laplacian Matrix, but in your code, the matrix is simplified. I guess the reason might be that the weights in the adjacency matrix are trainable, so it doesn't matter whether we initialize them with the Laplacian Matrix?

I will be grateful if you could reply to this issue.

chaoshangcs commented 4 years ago

Hi, Yes, your understanding is right. In this code, we use the edge types to assign the weights to the trainable adjacency matrix.