Some questions about the results of W-GCN represented in the paper

malllabiisc / CompGCN

ICLR 2020: Composition-Based Multi-Relational Graph Convolutional Networks

Apache License 2.0

597 stars 107 forks source link

Some questions about the results of W-GCN represented in the paper #8

Closed jianyucai closed 4 years ago

jianyucai commented 4 years ago

Hi, thanks for the code. I noticed that in your paper, you represent the results of DistMult + W-GCN in Table 4. But these results are not seen in the paper of W-GCN. I wonder where the results come from. Did you reproduce the results on your own?

Thanks.

svjan5 commented 4 years ago

Hi @tsaikenyoo, Yes, we have reproduced those results. W-GCN have provided their code on Github: https://github.com/JD-AI-Research-Silicon-Valley/SACN So, we just utilized it for getting those results.

Thanks and regards,