search

tkipf / gcn

Implementation of Graph Convolutional Networks in TensorFlow
MIT License
7.12k stars 2k forks source link

Can GCN be directly appied in an inductive setting? #79

Closed BenchengY closed 5 years ago

BenchengY commented 5 years ago

As far as I understand, it seems that GCN can be directly applied in an inductive setting. The only difference with the transductive setting is that, in the inference phase, we feed another graph Laplacian matrix into GCN.

tkipf commented 5 years ago

Yes exactly

On Sat 12. Jan 2019 at 10:37 CodeBB notifications@github.com wrote:

As far as I understand, it seems that GCN can be directly applied in an inductive setting. The only difference with the transductive setting is that, in the inference phase, we feed another graph Laplacian matrix into GCN.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/tkipf/gcn/issues/79, or mute the thread https://github.com/notifications/unsubscribe-auth/AHAcYOP9m_NlOBofNDNLcVDbwnKUT2zHks5vCazEgaJpZM4Z8k3g .

BenchengY commented 5 years ago

Thanks a lot for your so rapid reply!