NVIDIA / NVIDIA/cuvs

[FEA] KmeansPlusPlus Initialization Should Be Weighted

Open
#1,897 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

When sample weights are passed, the init sample chosen by KmeansPlusPlus should be weighted. Currently it is uniformly random. So if the user supplies weights, those are not taken into account in the init sample. Corresponding line in scikit-learn where the probabilities are scaled:
https://github.com/scikit-learn/scikit-learn/blob/ceeffc5d6e3494d4973472e7690ec8bce2f83b4e/sklearn/cluster/_kmeans.py#L263

Contributor guide

Open the contributing guide

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 by locating cuVS's KmeansPlusPlus initialization implementation and compare its initial-sample selection with the linked scikit-learn code, which scales probabilities using sample weights. Confirm how sample weights enter the clustering path, then verify that weighted inputs affect the initial sample selection while unweighted inputs retain current behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
scikit-learn
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.