-
Notifications
You must be signed in to change notification settings - Fork 3.7k
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
Support in_channels
with tuple
in GENConv
for bipartite message passing
#5627
Conversation
Codecov Report
@@ Coverage Diff @@
## master #5627 +/- ##
==========================================
- Coverage 83.87% 83.87% -0.01%
==========================================
Files 349 349
Lines 19196 19207 +11
==========================================
+ Hits 16101 16109 +8
- Misses 3095 3098 +3
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we add some corresponding tests?
torch_geometric/nn/conv/gen_conv.py
Outdated
channels.append(out_channels) | ||
self.mlp = MLP(channels, norm=norm) | ||
|
||
self.msg_norm = MessageNorm(learn_msg_scale) if msg_norm else None | ||
if in_channels[0] != in_channels[1]: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
and in_channels=[0] != -1
?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good point! Updated.
Sure. Will update it later. |
… passing (pyg-team#5627) * changelog * Support in_channels with tuple for bipartite message passing * changelog * update Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de> * support lazy init * Added test Co-authored-by: Guohao Li <lighaime@gmail.com> Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
This PR supports passing
in_channels
withtuple
toGENConv
for bipartite message passing by projecting channels to the same dimension if channels mismatch.