Added return_semantic_attention_weights parameter to HANConv
#5787
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov Report
@@ Coverage Diff @@
## master #5787 +/- ##
==========================================
- Coverage 83.97% 83.96% -0.02%
==========================================
Files 349 349
Lines 19422 19428 +6
==========================================
+ Hits 16309 16312 +3
- Misses 3113 3116 +3
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
rusty1s
changed the title
return_semantic_attention_weights parameter to HANConv
rusty1s
reviewed
Oct 20, 2022
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
rusty1s
approved these changes
Oct 20, 2022
JakubPietrakIntel
pushed a commit
to JakubPietrakIntel/pytorch_geometric
that referenced
this pull request
Nov 25, 2022
…-team#5787) Added return_semantic_attention_weights parameter to forward method of HANConv, in the same way GATConv returns its attention_weights. return_semantic_attention_weights (bool, optional): If set to :obj:`True`, will additionally return the tensor :obj:`semantic_attention_weights`, holding the computed attention weights for each edge type at semantic-level attention. (default: :obj:`None`). Further work could be dedicated to return also node-level attention weights as dictionary of (edge_type, attention_weights) items. Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
|
Does the return of conv.HANConv in torch_geometric contain the 2 parts tasks which are node-level attention and semantic-level attention in the paper? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Added return_semantic_attention_weights parameter to forward method of HANConv, in the same way GATConv returns its attention_weights.
return_semantic_attention_weights (bool, optional): If set to :obj:
True, will additionally return the tensor :obj:semantic_attention_weights, holding the computed attention weights for each edge type at semantic-level attention. (default: :obj:None).Further work could be dedicated to return also node-level attention weights as dictionary of (edge_type, attention_weights) items.