-
Notifications
You must be signed in to change notification settings - Fork 3.6k
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.
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
Relational Graph Attention #3359
Conversation
Codecov Report
@@ Coverage Diff @@
## master #3359 +/- ##
==========================================
- Coverage 81.54% 80.45% -1.10%
==========================================
Files 290 291 +1
Lines 14306 14538 +232
==========================================
+ Hits 11666 11696 +30
- Misses 2640 2842 +202
Continue to review full report at Codecov.
|
I still have plans to merge. Please leave it open. Sorry for the delay! |
for more information, see https://pre-commit.ci
# Conflicts: # .github/workflows/building-pyg-conda.yml # .github/workflows/building-rusty1s-conda.yml # .github/workflows/documentation.yml # .github/workflows/linting.yml # .github/workflows/testing.yml # torch_geometric/nn/conv/gcn_conv.py # torch_geometric/nn/conv/rgcn_conv.py
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
Closing this PR as just opened a new one for this implementation with PR number: #4031 |
Added Relational Graph Attention Networks, which computes attention coefficients for relational graphs for each relation type for any number of relations and attention heads. Moreover, also provides functionality for edge attributes to handle.