Skip to content
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

Update message_passing.py #4418

Merged
merged 2 commits into from
Apr 6, 2022
Merged

Update message_passing.py #4418

merged 2 commits into from
Apr 6, 2022

Conversation

irrational1005
Copy link
Contributor

@irrational1005 irrational1005 commented Apr 5, 2022

When using a bipartite graph for reverse message passing(set flow = 'target_to_source'), the message aggregation fails or returns a tensor of the wrong dimension due to incorrect dim_size, although it doesn't really matter and different edge_index can be used to achieve the same effect.
ps:I'm new to pyg, so please forgive me if it's not correct.

Unverified

This commit is not signed, but one or more authors requires that any commit attributed to them is signed.
When using a bipartite graph for reverse message passing(set flow == 'target_to_source'), the message construction fails due to incorrect dim_size, although it doesn't matter, and different adjacency matrices can be used to achieve the same effect.
@codecov
Copy link

codecov bot commented Apr 5, 2022

Codecov Report

Merging #4418 (cc869b7) into master (2f6fdef) will not change coverage.
The diff coverage is 100.00%.

@@           Coverage Diff           @@
##           master    #4418   +/-   ##
=======================================
  Coverage   82.59%   82.59%           
=======================================
  Files         312      312           
  Lines       16113    16113           
=======================================
  Hits        13308    13308           
  Misses       2805     2805           
Impacted Files Coverage Δ
torch_geometric/nn/conv/message_passing.py 99.40% <100.00%> (ø)

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 2f6fdef...cc869b7. Read the comment docs.

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
@irrational1005 irrational1005 deleted the patch-1 branch April 6, 2022 09:32
@irrational1005 irrational1005 restored the patch-1 branch April 6, 2022 09:36
@irrational1005 irrational1005 reopened this Apr 6, 2022
Copy link
Member

@rusty1s rusty1s left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for catching!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants