Skip to content

Implement error check for negative edge weights in GCNConv #10549

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
vertumnal wants to merge 4 commits into
base: master
Choose a base branch
from
+7 −0
Open

Implement error check for negative edge weights in GCNConv #10549

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1ec3ccc
Implement error check for negative edge weights
vertumnal Dec 9, 2025
029b9a0
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Dec 9, 2025
8037fd9
Fixed GCNConv.forward to raise an error in case edge_weight has negat…
vertumnal Dec 9, 2025
5c35678
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Dec 9, 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
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 @@ -15,6 +15,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).

### Fixed

- Fixed GCNConv.forward to raise an error in case edge_weight has negative values ([#10549](https://github.com/pyg-team/pytorch_geometric/pull/10549))

### Security

## [2.7.0] - 2025-10-14
Expand Down
5 changes: 5 additions & 0 deletions torch_geometric/nn/conv/gcn_conv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -234,6 +234,11 @@ def forward(self, x: Tensor, edge_index: Adj,
f"Please try other layers such as 'SAGEConv' or "
f"'GraphConv' instead")

if edge_weight is not None and (edge_weight < 0).any().item():
raise ValueError(f"'{self.__class__.__name__}' does not support "
f"negative edge weights as input. Please try "
f"'SignedConv' instead if they are necessary.")

if self.normalize:
if isinstance(edge_index, Tensor):
cache = self._cached_edge_index
Expand Down