Skip to content

[cuGraph] Fix test_gat_conv_equality for new edge_attr requirement in CuGraphGATConv #10564

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

Open
drivanov wants to merge 2 commits into
base: master
Choose a base branch
from
+10 −13
Open

[cuGraph] Fix test_gat_conv_equality for new edge_attr requirement in CuGraphGATConv #10564

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
ef32e0f
Fixing test_gat_conv_equality.
drivanov Dec 20, 2025
d543155
Updating CHANGELOG.md
drivanov Dec 22, 2025
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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).

### Fixed

- Fixed `test_gat_conv_equality` to explicitly handle `edge_attr` argument in CuGraphGATConv.forward ([#10564](https://github.com/pyg-team/pytorch_geometric/pull/10564))
- Fixed `ogbn_train_cugraph` example for distributed cuGraph ([#10439](https://github.com/pyg-team/pytorch_geometric/pull/10439))
- Added `safe_onnx_export` function with workarounds for `onnx_ir.serde.SerdeError` issues in ONNX export ([#10422](https://github.com/pyg-team/pytorch_geometric/pull/10422))
- Fixed importing PyTorch Lightning in `torch_geometric.graphgym` and `torch_geometric.data.lightning` when using `lightning` instead of `pytorch-lightning` ([#10404](https://github.com/pyg-team/pytorch_geometric/pull/10404), [#10417](https://github.com/pyg-team/pytorch_geometric/pull/10417)))
Expand Down
22 changes: 9 additions & 13 deletions test/nn/conv/cugraph/test_cugraph_gat_conv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,27 +34,23 @@ def test_gat_conv_equality(bias, bipartite, concat, edge_attr, heads,
conv2.lin.weight.data[:, :] = conv1.lin.weight.data
conv2.att.data[:heads * out_channels] = conv1.att_src.data.flatten()
conv2.att.data[heads * out_channels:] = conv1.att_dst.data.flatten()

if edge_attr and not bipartite:
e_attrs = torch.randn(size=(edge_index.size(1), 10))
e_attrs = torch.randn(edge_index.size(1), 0, device=x.device)
out1 = conv1(x, edge_index, edge_attr=e_attrs)

out2 = conv2(
x,
EdgeIndex(edge_index, sparse_size=size),
max_num_neighbors=max_num_neighbors,
edge_attr=e_attrs,
)
else:
e_attrs = None
if bipartite:
out1 = conv1((x, x[:size[1]]), edge_index)
else:
out1 = conv1(x, edge_index)

out2 = conv2(
x,
EdgeIndex(edge_index, sparse_size=size),
max_num_neighbors=max_num_neighbors,
)
out2 = conv2(
x,
EdgeIndex(edge_index, sparse_size=size),
max_num_neighbors=max_num_neighbors,
edge_attr=e_attrs,
)
assert torch.allclose(out1, out2, atol=1e-3)

grad_output = torch.rand_like(out1)
Expand Down
Loading