Batch operations about pygcn HOT 6 OPEN

Hi @evanfeinberg, thanks! It was a pleasure meeting you as well. I posted a solution for this problem some time ago in this thread (from the gcn repository): tkipf/gcn#4 . I had an implementation of this some time earlier last year already and if I remember correctly, results were comparable (or sometimes better) when compared to the method by Niepert et al. (ICML 2016) for batch-wise graph classification. So inductive learning with this type of model (contrary to common belief) is indeed very much possible. I haven't put it in the ICLR paper due to time constraints (and spatial constraints).

To re-state the solution over here: multiple graphs can be fed as a single sparse block-diagonal adjacency matrix, and graph-level classification can be done by adding a global "hub" node that is connected to all other nodes (this was suggested already back in 2009 by Scarselli et al.).

from pygcn.

Thank you for the speedy response, @tkipf ! The workaround of a block diagonal sparse matrix consisting of individual adjacency matrices makes a lot of sense. I will try and report back!

from pygcn.

@tkipf thanks for the package, it is really useful.
Will it be possible to share your code that switches a batch of graphs into a diagonal blocks matrix. I found a scipy implementation. But maybe you managed to use a pytorch built-in functions, which will be much more efficient.

from pygcn.

from pygcn.

@idansc Hi, can you provide a link address code for the scipy implementation ?

from pygcn.

@malizheng see scipy.linalg.block_diag

from pygcn.