pg.ddx.io  pgvector/pgvector GitHub issues and pull requests  
help / color / mirror / Atom feed
From: SunnyBo0302 (@SunnyBo0302) <noreply+SunnyBo0302@github.com>
To: pgvector/pgvector <noreply+pgvector-pgvector@github.com>
Subject: [pgvector/pgvector] issue #1065: Support for Advanced K-means Acceleration Techniques in IVFFlat Index Construction
Date: Mon, 16 Nov 2026 13:44:40 +0000
Message-ID: <gh-pgvector-pgvector-1065@github.com> (raw)

Hi, thank you for developing and maintaining pgvector!

I was wondering whether there are any plans to explore advanced K-means acceleration techniques, such as:

- **[[SuperKMeans](https://github.com/cwida/SuperKMeans)](https://github.com/cwida/SuperKMeans)** — [[Paper](https://arxiv.org/abs/2603.20009)](https://arxiv.org/abs/2603.20009)
- **[[e-means](https://e-means.github.io/)](https://e-means.github.io/)** — [[Paper](https://arxiv.org/abs/2611.09501)](https://arxiv.org/abs/2611.09501)

Both approaches have demonstrated promising improvements in K-means clustering efficiency.

Have these approaches been considered, or would there be interest in incorporating similar optimizations to accelerate IVFFlat index construction in pgvector?

I'd appreciate any thoughts on their potential applicability.

view thread (4+ messages)  latest in thread

Message-ID: <gh-pgvector-pgvector-1065@github.com>
Permalink:  ../gh-pgvector-pgvector-1065@github.com/

 · 


This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox