Preprint · 2018 · Open access

Hyperbolic Entailment Cones for Learning Hierarchical Embeddings

Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann

arXiv (Cornell University), 4, 1646–1655 · Published 3 April 2018 · DOI 10.48550/arxiv.1804.01882

Open PDFView at the publisherCite this paper

In brief

“Hyperbolic Entailment Cones for Learning Hierarchical Embeddings” is a 2018 preprint by Octavian-Eugen Ganea and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 305 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
305
Most cited in
2026 (61)
References
33
Authors
3

Abstract

Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning. We here present a novel method to embed directed acyclic graphs. Following prior work, we first advocate for using hyperbolic spaces which provably model tree-like structures better than Euclidean geometry. Second, we view hierarchical relations as partial orders defined using a family of nested geodesically convex cones. We prove that these entailment cones admit an optimal shape with a closed form expression both in the Euclidean and hyperbolic spaces, and they canonically define the embedding learning process. Experiments show significant improvements of our method over strong recent baselines both in terms of representational capacity and generalization.

Cite this paper

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

APA 7

Ganea, O.-E., Bécigneul, G., & Hofmann, T. (2018). Hyperbolic Entailment Cones for Learning Hierarchical Embeddings. arXiv (Cornell University), 4, 1646–1655. https://doi.org/10.48550/arxiv.1804.01882

MLA 9

Ganea, Octavian-Eugen, et al. “Hyperbolic Entailment Cones for Learning Hierarchical Embeddings.” arXiv (Cornell University), vol. 4, 2018, pp. 1646–1655. https://doi.org/10.48550/arxiv.1804.01882.

Chicago

Ganea, Octavian-Eugen, Gary Bécigneul, and Thomas Hofmann. 2018. “Hyperbolic Entailment Cones for Learning Hierarchical Embeddings.” arXiv (Cornell University) 4: 1646–1655. https://doi.org/10.48550/arxiv.1804.01882.

Harvard

Ganea, O.-E., Bécigneul, G. and Hofmann, T. (2018) ‘Hyperbolic Entailment Cones for Learning Hierarchical Embeddings’, arXiv (Cornell University), 4, pp. 1646–1655. doi:10.48550/arxiv.1804.01882.

IEEE

O.-E. Ganea, G. Bécigneul, and T. Hofmann, “Hyperbolic Entailment Cones for Learning Hierarchical Embeddings,” arXiv (Cornell University), vol. 4, pp. 1646–1655, 2018, doi: 10.48550/arxiv.1804.01882.

BibTeX

@misc{ganea2018hyperbolic,
  title     = {{Hyperbolic Entailment Cones for Learning Hierarchical Embeddings}},
  author    = {Ganea, Octavian-Eugen and Bécigneul, Gary and Hofmann, Thomas},
  howpublished = {arXiv (Cornell University)},
  year      = {2018},
  volume    = {4},
  pages     = {1646--1655},
  doi       = {10.48550/arxiv.1804.01882},
  url       = {https://doi.org/10.48550/arxiv.1804.01882}
}

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

Citations by year

YearCitationsShare of the best year
20181010
20193333
20203535
20214545
20222323
20233131
20242828
20253939
20266161

Topic and keywords

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

  • hyperbolic embeddings
  • directed acyclic graphs
  • hierarchical embedding
  • partially ordered sets
  • graph representation learning
  • tree-like structures
  • hyperbolic geometry

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?

Ganea, O.-E., Bécigneul, G., & Hofmann, T. (2018). Hyperbolic Entailment Cones for Learning Hierarchical Embeddings. arXiv (Cornell University), 4, 1646–1655. https://doi.org/10.48550/arxiv.1804.01882

How many times has this paper been cited?

305 times, according to OpenAlex on 19 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?

Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann.

What is the DOI of this paper?

10.48550/arxiv.1804.01882, permanently at https://doi.org/10.48550/arxiv.1804.01882. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.