Skip to content

Slice GNNRecurrence input by indexing instead of eachslice views #707

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
CarloLucibello merged 2 commits into from
Aug 26, 2026
Merged

Slice GNNRecurrence input by indexing instead of eachslice views #707

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f25978d
Slice GNNRecurrence input by indexing instead of eachslice views
Parvm1102 Aug 24, 2026
82db2b2
Merge branch 'master' into enzyme-recurrence-slices
CarloLucibello Aug 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@ Entries link to the pull request that introduced them.
## GraphNeuralNetworks.jl — Unreleased (towards 1.1.1)

**Changed**
- `GNNRecurrence` now hands each cell an indexed time slice instead of an `eachslice` view, matching the Lux frontend. Enzyme's type analysis fails on `SubArray` cell inputs, so this unblocks `DCGRU`, `EvolveGCNO`, `GConvGRU` and `GConvLSTM` under Enzyme ([#707]).
- The recurrent temporal cells now delegate their forward-pass math to shared `GNNlib` functions (requires GNNlib ≥ 1.4); the layer behaviour is unchanged ([#696]).

## GNNlib.jl 1.4.0 — 2026-07-22
Expand Down Expand Up @@ -235,5 +236,6 @@ Lux implementations of the graph convolutional, pooling, and temporal layers
[#696]: https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/pull/696
[#703]: https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/pull/703
[#704]: https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/pull/704
[#707]: https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/pull/707
[#706]: https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/pull/706
[FluxML/Zygote.jl#1662]: https://github.com/FluxML/Zygote.jl/issues/1662
6 changes: 4 additions & 2 deletions GraphNeuralNetworks/src/layers/temporalconv.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
function scan(cell, g::GNNGraph, x::AbstractArray{T,3}, state) where {T}
y = []
for xt in eachslice(x, dims = 2)
yt, state = cell(g, xt, state)
for t in 1:size(x, 2)
# slice by indexing, not `eachslice`: Enzyme's type analysis fails on
# `SubArray` cell inputs. The Lux frontend slices the same way.
yt, state = cell(g, x[:, t, :], state)
y = vcat(y, [yt])
end
return stack(y, dims = 2)
Expand Down