Run with relation basis vectors

malllabiisc / CompGCN

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

Apache License 2.0

597 stars 107 forks source link

Run with relation basis vectors #6

Closed gsp2014 closed 4 years ago

gsp2014 commented 4 years ago

Hi, Thank you for this wonderful work! I got the following error when I ran with "-num_bases 50" (as suggested in the paper): AttributeError: 'CompGCNConvBasis' object has no attribute 'cache'. Can I just remove Lines 40 and 41 in compgcn_conv_basis.py?

soumyasanyal commented 4 years ago

Yes, removing that should work fine, but the cache is useful for the link prediction and node classification tasks where we're operating on the same graph at each iteration. Right now, the code does the norm calculations for each iteration. I've made changes to the file in this commit. Feel free to close this after pulling the new changes. Let us know in case of further issues.

gsp2014 commented 4 years ago

Thank you very much for your prompt reply!