Bridging ML and algorithms: comparison of hyperbolic embeddings

Dorota Celińska-Kopczyńska, Eryk Kopczyński

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: hyperbolic embeddings

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: compare the performance of hyperbolic embeddings obtained in algorithm / social network / machine learning communities

Abstract: Hyperbolic embeddings are well-studied both in the machine learning and algorithm community. However, as the research proceeds independently in those two communities, comparisons and even awareness seem to be currently lacking. We compare the performance (time needed to compute embeddings) and the quality of the embeddings obtained by the popular approaches, both on real-life hierarchies and networks and simulated networks. In particular, according to our results, the algorithm by Bläsius et al (ESA 2016) is about 100 times faster than the Poincaré embeddings (NIPS 2017) and Lorentz embeddings (ICML 2018) by Nickel and Kiela, while achieving results of similar (or, in some cases, even better) quality.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 50