Low-dimensional embeddings of high-dimensional data
Abstract
Large collections of high-dimensional data have become nearly ubiquitous across many academic fields and application domains, ranging from biology to the humanities. Since working directly with high-dimensional data poses challenges, the demand for algorithms that create low-dimensional representations, or embeddings, for data visualization, exploration, and analysis is now greater than ever. In recent years, numerous embedding algorithms have been developed, and their usage has become widespread in research and industry. This surge of interest has resulted in a large and fragmented research field that faces technical challenges alongside fundamental debates, and it has left practitioners without clear guidance on how to effectively employ existing methods. Aiming to increase coherence and facilitate future work, in this review we provide a detailed and critical overview of recent developments, derive a list of best practices for creating and using low-dimensional embeddings, evaluate popular approaches on a variety of datasets, and discuss the remaining challenges and open problems in the field.
Cite
@article{arxiv.2508.15929,
title = {Low-dimensional embeddings of high-dimensional data},
author = {Cyril de Bodt and Alex Diaz-Papkovich and Michael Bleher and Kerstin Bunte and Corinna Coupette and Sebastian Damrich and Enrique Fita Sanmartin and Fred A. Hamprecht and Emőke-Ágnes Horvát and Dhruv Kohli and Smita Krishnaswamy and John A. Lee and Boudewijn P. F. Lelieveldt and Leland McInnes and Ian T. Nabney and Maximilian Noichl and Pavlin G. Poličar and Bastian Rieck and Guy Wolf and Gal Mishne and Dmitry Kobak},
journal= {arXiv preprint arXiv:2508.15929},
year = {2025}
}
Comments
This work was the result of Dagstuhl Seminar 24122