What is the model architectural difference between transductive GCN and inductive GraphSAGE?
guotong1988 opened this issue · comments
Difference of the model design.
It seems the difference is that GraphSAGE sample the data.
But what is the difference in model architecture.
Thank you very much.
Thank you very much.
No worries :) I'll leave this open since this question seems to appear quite frequently (so others can more easily find it).
I have a followup question.
I noticed that, despite what said above by @tkipf, Pytorch Geometric has a different implementation for GraphSAGE and GCN. To the best of my knowledge the neighbors subsampling is implemented by NeighborLoader
(an 'external' DataLoader), so I haven't understood why keeping two separate implementations.
In addition, by looking at the PyG documentation:
So, it seems that the difference between the two is that GraphSAGE runs a simple mean of nearby embeddings, while GCN applies a weighted mean, with weights the normalization coefficients.
Is this the right architectural difference or is just a PyG implementation difference?
Thanks