[KGE] Add evaluate logic #343
Draft
Conversation
This file contains hidden or 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
svij-sc
reviewed
Oct 1, 2025
python/gigl/experimental/knowledge_graph_embedding/lib/evaluation.py
Outdated
Show resolved
Hide resolved
svij-sc
reviewed
Oct 1, 2025
python/gigl/experimental/knowledge_graph_embedding/lib/evaluation.py
Outdated
Show resolved
Hide resolved
svij-sc
reviewed
Oct 1, 2025
python/gigl/experimental/knowledge_graph_embedding/lib/evaluation.py
Outdated
Show resolved
Hide resolved
nshah-sc
commented
Oct 2, 2025
Comment on lines
+147
to
+150
| def compute_final_metrics( | ||
| self, | ||
| unique_edge_types: List[CondensedEdgeType], | ||
| ) -> EvaluationResult: |
Collaborator
Author
There was a problem hiding this comment.
currently keeping this API because other code that i haven't pushed relies on this and will be a mess to manage this change, however i can anticipate in future dropping EvaluationResult and EdgeTypeMetrics to instead just interface with the EvaluationMetricsAccumulator itself.
svij-sc
approved these changes
Oct 23, 2025
|
|
||
| # Restore original model state | ||
| pipeline._model.module.set_phase(original_phase) | ||
| pipeline._model.train() |
Collaborator
There was a problem hiding this comment.
only enable training if "was_training" before?
|
|
||
| # Process each edge type | ||
| for edge_type, idx in self._edge_type_to_idx.items(): | ||
| edge_type_mask = condensed_edge_types == edge_type |
Collaborator
There was a problem hiding this comment.
flip this so you iterate through condensed_edge_types instead?
i.e.
for condensed_edge_type in condensed_edge_types:
idx = _edge_type_to_idx[condensed_edge_type]
...
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.
Add code which computes the evaluation metrics for KGE training.
Main entrypoint is
evaluatewhich just calls other private functions for organization.Where is the documentation for this feature?: N/A
Did you add automated tests or write a test plan?
Updated Changelog.md? NO
Ready for code review?: YES