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

[NeurIPS 2023 Sparse Track] FDUx2-shnsw Submission #198

Merged
merged 2 commits into from
Oct 31, 2023

Conversation

matchyc
Copy link
Contributor

@matchyc matchyc commented Oct 30, 2023

Team FDUx2 intends to submit multiple tracks under the name FDUx2-<algorithm-name>, and here is FDUx2-shnsw for Sparse Track.
We would like to express our gratitude to the organizers for your patient evaluation.

Signed-off-by: Meng Chen <[email protected]>
@matchyc matchyc changed the title FDU x2 shnsw [NeurIPS 2023 OOD Track] FDUx2-shnsw Submission Oct 30, 2023
@matchyc matchyc changed the title [NeurIPS 2023 OOD Track] FDUx2-shnsw Submission [NeurIPS 2023 Sparse Track] FDUx2-shnsw Submission Oct 30, 2023
Copy link
Collaborator

@ingberam ingberam left a comment

Choose a reason for hiding this comment

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

LGTM, code builds and runs on a VM with 8cpu/16GB memory (GCP n2-custom-8-16384).

@matchyc: please approve that these results are roughly what you would expect?

shnsw,sparse_hnswlib,sparse-full,10,12177.737054397963,0.0,29630.818413734436,11034980.0,0,0,sparse,0.7994269340974212
shnsw,sparse_hnswlib,sparse-full,10,7947.033044411104,0.0,29630.818413734436,11034980.0,0,0,sparse,0.8854297994269341
shnsw,sparse_hnswlib,sparse-full,10,7367.327526288479,0.0,29630.818413734436,11034980.0,0,0,sparse,0.8951002865329514
shnsw,sparse_hnswlib,sparse-full,10,7048.045510025735,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9010458452722062
shnsw,sparse_hnswlib,sparse-full,10,6848.650637956033,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9048137535816618
shnsw,sparse_hnswlib,sparse-full,10,6667.224295496154,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9072206303724929
shnsw,sparse_hnswlib,sparse-full,10,6394.325862427465,0.0,29630.818413734436,11034980.0,0,0,sparse,0.911404011461318
shnsw,sparse_hnswlib,sparse-full,10,6247.696169337714,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9134527220630373
shnsw,sparse_hnswlib,sparse-full,10,5375.535588116485,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9266189111747851
shnsw,sparse_hnswlib,sparse-full,10,5106.970919323923,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9309312320916906
shnsw,sparse_hnswlib,sparse-full,10,4847.612098861592,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9353008595988539
shnsw,sparse_hnswlib,sparse-full,10,4642.8395496375015,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9382091690544412
shnsw,sparse_hnswlib,sparse-full,10,4442.987157238651,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9417335243553009

@matchyc
Copy link
Contributor Author

matchyc commented Oct 31, 2023

LGTM, code builds and runs on a VM with 8cpu/16GB memory (GCP n2-custom-8-16384).

@matchyc: please approve that these results are roughly what you would expect?

shnsw,sparse_hnswlib,sparse-full,10,12177.737054397963,0.0,29630.818413734436,11034980.0,0,0,sparse,0.7994269340974212
shnsw,sparse_hnswlib,sparse-full,10,7947.033044411104,0.0,29630.818413734436,11034980.0,0,0,sparse,0.8854297994269341
shnsw,sparse_hnswlib,sparse-full,10,7367.327526288479,0.0,29630.818413734436,11034980.0,0,0,sparse,0.8951002865329514
shnsw,sparse_hnswlib,sparse-full,10,7048.045510025735,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9010458452722062
shnsw,sparse_hnswlib,sparse-full,10,6848.650637956033,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9048137535816618
shnsw,sparse_hnswlib,sparse-full,10,6667.224295496154,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9072206303724929
shnsw,sparse_hnswlib,sparse-full,10,6394.325862427465,0.0,29630.818413734436,11034980.0,0,0,sparse,0.911404011461318
shnsw,sparse_hnswlib,sparse-full,10,6247.696169337714,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9134527220630373
shnsw,sparse_hnswlib,sparse-full,10,5375.535588116485,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9266189111747851
shnsw,sparse_hnswlib,sparse-full,10,5106.970919323923,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9309312320916906
shnsw,sparse_hnswlib,sparse-full,10,4847.612098861592,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9353008595988539
shnsw,sparse_hnswlib,sparse-full,10,4642.8395496375015,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9382091690544412
shnsw,sparse_hnswlib,sparse-full,10,4442.987157238651,0.0,29630.818413734436,11034980.0,0,0,sparse,0.9417335243553009

The results match our observation, thank you for your feedback.

@ingberam ingberam merged commit a439f6d into harsha-simhadri:main Oct 31, 2023
14 checks passed
@Leslie-Chung
Copy link

@ingberam Hi! We see that some people are still submitting, if it is still possible to change the parameters please let me know!

@matchyc
Copy link
Contributor Author

matchyc commented Nov 20, 2023

@harsha-simhadri Same entry from one team, thank you for your reminder!

Conference Name: Practical Vector Search Challenge: NeurIPS 2023 Competition track
Paper ID: 15
Paper Title: Fast OOD-ANN

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.

3 participants