English

Manify: A Python Library for Learning Non-Euclidean Representations

Machine Learning 2025-07-18 v2

Abstract

We present Manify, an open-source Python library for non-Euclidean representation learning. Leveraging manifold learning techniques, Manify provides tools for learning embeddings in (products of) non-Euclidean spaces, performing classification and regression with data that lives in such spaces, estimating the curvature of a manifold, and more. Manify aims to advance research and applications in machine learning by offering a comprehensive suite of tools for manifold-based data analysis. Our source code, examples, and documentation are available at https://github.com/pchlenski/manify.

Keywords

Cite

@article{arxiv.2503.09576,
  title  = {Manify: A Python Library for Learning Non-Euclidean Representations},
  author = {Philippe Chlenski and Kaizhu Du and Dylan Satow and Raiyan R. Khan and Itsik Pe'er},
  journal= {arXiv preprint arXiv:2503.09576},
  year   = {2025}
}

Comments

33 pages, 4 figures, 5 tables. Preprint

R2 v1 2026-06-28T22:17:52.446Z