Add DConv layer
#441
Merged
Add DConv layer
#441
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| h = l.weights[1,1,:,:] * x .+ l.weights[2,1,:,:] * x | ||
|
|
||
| T0 = x | ||
| if l.K > 1 |
There was a problem hiding this comment.
For K=1 this layer is the identity, is that correct?
src/layers/conv.jl
Outdated
| end | ||
|
|
||
| function (l::DConv)(g::GNNGraph, x::AbstractMatrix) | ||
| A = adjacency_matrix(g, weighted = true) |
There was a problem hiding this comment.
Instead of materializing the adjacency matrix, which currently gives a dense matrix on gpu therefore inconvenient for large graphs, the operations should be expressed through the propagate framework that relies on gather/scatter.
There was a problem hiding this comment.
I have not found a way to use propagate on the transpose adjacency matrix. Should I implement the Graphs.reverse function for GNNGraph to do this?(but probably will not be GPU compatible)
There was a problem hiding this comment.
I manage to create the reverse of the graph and it is GPU compatible.
Co-authored-by: Carlo Lucibello <[email protected]>
Co-authored-by: Carlo Lucibello <[email protected]>
Co-authored-by: Carlo Lucibello <[email protected]>
Co-authored-by: Carlo Lucibello <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds the Diffusion Convolutional Layer of the following paper https://arxiv.org/pdf/1707.01926