Preprint · 2017 · Open access

Poincaré Embeddings for Learning Hierarchical Representations

Maximilian Nickel, Douwe Kiela

arXiv (Cornell University) · Published 22 May 2017 · DOI 10.48550/arxiv.1705.08039

Open PDFView at the publisherCite this paper

In brief

“Poincaré Embeddings for Learning Hierarchical Representations” is a 2017 preprint by Maximilian Nickel and Douwe Kiela, published in arXiv (Cornell University). OpenAlex counts 1,101 citations as of 22 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
1,101
Most cited in
2026 (176)
References
32
Authors
2

Abstract

Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically learn embeddings in Euclidean vector spaces, which do not account for this property. For this purpose, we introduce a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an n-dimensional Poincaré ball. Due to the underlying hyperbolic geometry, this allows us to learn parsimonious representations of symbolic data by simultaneously capturing hierarchy and similarity. We introduce an efficient algorithm to learn the embeddings based on Riemannian optimization and show experimentally that Poincaré embeddings outperform Euclidean embeddings significantly on data with latent hierarchies, both in terms of representation capacity and in terms of generalization ability.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Nickel, M., & Kiela, D. (2017). Poincaré Embeddings for Learning Hierarchical Representations. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1705.08039

MLA 9

Nickel, Maximilian, and Douwe Kiela. “Poincaré Embeddings for Learning Hierarchical Representations.” arXiv (Cornell University), 2017. https://doi.org/10.48550/arxiv.1705.08039.

Chicago

Nickel, Maximilian and Douwe Kiela. 2017. “Poincaré Embeddings for Learning Hierarchical Representations.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1705.08039.

Harvard

Nickel, M. and Kiela, D. (2017) ‘Poincaré Embeddings for Learning Hierarchical Representations’, arXiv (Cornell University). doi:10.48550/arxiv.1705.08039.

IEEE

M. Nickel and D. Kiela, “Poincaré Embeddings for Learning Hierarchical Representations,” arXiv (Cornell University), 2017, doi: 10.48550/arxiv.1705.08039.

BibTeX

@misc{nickel2017poincar,
  title     = {{Poincaré Embeddings for Learning Hierarchical Representations}},
  author    = {Nickel, Maximilian and Kiela, Douwe},
  howpublished = {arXiv (Cornell University)},
  year      = {2017},
  doi       = {10.48550/arxiv.1705.08039},
  url       = {https://doi.org/10.48550/arxiv.1705.08039}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201777
20185050
2019110110
2020168168
2021175175
20227272
2023101101
2024126126
2025116116
2026176176

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks

  • Poincaré embeddings
  • hyperbolic space
  • hierarchical representation
  • symbolic data
  • Riemannian optimization
  • hyperbolic geometry
  • embedding learning
  • generalization

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Nickel, M., & Kiela, D. (2017). Poincaré Embeddings for Learning Hierarchical Representations. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1705.08039

How many times has this paper been cited?

1,101 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Maximilian Nickel, Douwe Kiela.

What is the DOI of this paper?

10.48550/arxiv.1705.08039, permanently at https://doi.org/10.48550/arxiv.1705.08039. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.