microsoft / microsoft/SPTAG

How can I reproduce Figure 6 and 8 in SPANN article.

Open
#262 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
5k
Forks
622
Avg merge
8h 37m
Merged PRs (30d)
5

Description

I want to reproduce Figure 6 and 8 in SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search by using https://github.com/microsoft/SPTAG/commit/216a17ae656c5fd594aa3cc1b4ea1be72bcc3e4d.
Can anybody let me know about the followings to reproduce them?

  • procedure, contents of a buildconfig.ini, and all values of parameters.
    • Especially, which parameter(s) do I need to change to get each plot.
  • differences between IndexAlgoType in buildconfig.ini and -a of indexbuilder

And, I encountered following errors.

  • When I use buildconfig.ini in docs/GettingStart.md and set spann to both of IndexAlgoType and -a, SEGV happened.
  • When I use buildconfig.ini in docs/GettingStart.md and set bkt or kdt to both of IndexAlgoType and -a, Failed to build index error happened.

Are they invalid settings?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with docs/GettingStart.md, the referenced SPTAG commit, and the indexbuilder entry point; compare IndexAlgoType with the -a option and the SPANN paper's Figure 6 and 8 setup. Reproduce the reported SEGV and failed index builds, then document the procedure, complete buildconfig.ini values, plot-specific parameters, and valid settings.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
search
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.