Add Navigating Spreading-Out Graph (NSG) #611
Open
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
Currently, one of the state-of-the-art algorithms, the Navigating Spreading-out Graph (NSG), is missing in the benchmark. Add NSG to the set of algorithms. Since NSG does not support non-metric distances, add L2 and normalize + L2 to handle cosine similarity. Add Dockerfile, add to unit tests.
Reduce runtime by only including config options specified in the paper or on the github of NSG.
Author
|
@erikbern @maumueller Thanks for the great work on this benchmark. I'd really appreciate it if one of you could review and let me know if you want anything changed. Thanks! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
NSG [1] is one of the state-of-the-art algorithms according to recent surveys [2] but still missing in the benchmark.
Add NSG along with a very rudimentary configuration (based on what the authors said they used for gist and sift datasets) because NSG takes a bit longer to build compared to other indices. The NSG module uses Python bindings called pynsg that are a wrapper around the reference implementation [3].
Fix issue #112
[1] https://arxiv.org/pdf/1707.00143
[2] https://dl.acm.org/doi/abs/10.1145/3709693
[3] https://github.com/ZJULearning/nsg