Skip to content

Trepetsky/embedding-metrics

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

embedding-metrics

This is an implementation of metrics for unsupervised embedding quality evaluation on Jax, based on the paper "Unsupervised Embedding Quality Evaluation".

The original code in numpy can be found here: https://github.com/google-research/google-research/tree/master/graph_embedding/metrics

With the application of Jax, computations were able to be accelerated ~2x on CPU and ~15x on GPU on my hardware.

Citation

Tsitsulin, A., Munkhoeva, M., & Perozzi, B. (2023). Unsupervised Embedding Quality Evaluation. Paper

About

Metrics for evaluating unsupervised embeddings.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages