[WIP][BUG] Fix CAGRA search recall with a graph built by NN Descent #819
+113
−48
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
enp1s0
added
bug
tfeher
requested changes
Apr 23, 2025
| @@ -829,36 +830,29 @@ void GnndGraph<Index_t>::sample_graph_new(InternalID_t<Index_t>* new_neighbors, | |||
| template <typename Index_t> | |||
| void GnndGraph<Index_t>::init_random_graph() | |||
There was a problem hiding this comment.
Could you add a docstring to describe what properties the random graph is expected to have? What is ensured by the current PR to fix the low recall issue? E.g. is it guaranteed to be fully connected?
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Outdated suggestions cannot be applied.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.
This PR addresses an unexpected low recall issue in the CAGRA search with a graph generated by NN Descent.
For that, it updates the initial NN Descent graph generation so that all indices are included, whereas some nodes are not found in the branch-25.06 implementation.
This PR also makes the following changes: