Skip to content

Hypergat layer edge attention fix pr #337

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
tz545 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Hypergat layer edge attention fix pr #337

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b5993e0
fixed bug to change second attention calculation for HyperGat layer t…
tz545 Jun 10, 2025
aa9ecd2
fixed error with source and target index in attention function
tz545 Jun 11, 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
10 changes: 5 additions & 5 deletions topomodelx/nn/hypergraph/hypergat_layer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ def attention(
Attention weights: one scalar per message between a source and a target cell.
"""
if mechanism == "node-level":
x_source_per_message = x_source[self.target_index_i]
x_source_per_message = x_source[self.source_index_j]
return torch.nn.functional.softmax(
torch.matmul(
torch.nn.functional.leaky_relu(x_source_per_message),
Expand All @@ -122,11 +122,11 @@ def attention(
dim=1,
)

x_source_per_message = x_source[self.source_index_j]
x_source_per_message = x_source[self.target_index_i]
x_target_per_message = (
x_source[self.target_index_i]
if x_target is None
else x_target[self.target_index_i]
else x_target[self.source_index_j]
)

x_source_target_per_message = torch.nn.functional.leaky_relu(
Expand Down Expand Up @@ -183,7 +183,7 @@ def forward(self, x_0, incidence_1):
Output hyperedge features.
"""
intra_aggregation = incidence_1.t() @ (x_0 @ self.weight1)

self.target_index_i, self.source_index_j = incidence_1.indices()

attention_values = self.attention(intra_aggregation).squeeze()
Expand All @@ -200,7 +200,7 @@ def forward(self, x_0, incidence_1):
inter_aggregation = incidence_1 @ (messages_on_edges @ self.weight2)

attention_values = self.attention(
inter_aggregation, intra_aggregation
inter_aggregation, intra_aggregation, "edge-level"
).squeeze()
incidence_with_attention = torch.sparse_coo_tensor(
indices=incidence_1.indices(),
Expand Down