Conference paper · 2022 · Open access

Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design

Xiran Fan, Chun-Hao Yang, Baba C. Vemuri

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2022, 356–365 · Published 1 June 2022 · DOI 10.1109/cvpr52688.2022.00045

Open full textView at the publisherCite this paper

In brief

“Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design” is a 2022 conference paper by Xiran Fan and 2 co-authors, published in IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings. OpenAlex counts 25 citations as of 20 November 2026, which puts it in the top 6% of works published in 2022 by citations. It is open access: the full text is free to read at PubMed Central.

Citations
25
Most cited in
2024 (12)
Field-weighted impact
1.43
References
49
Authors
3

Abstract

Hyperbolic neural networks have been popular in the recent past due to their ability to represent hierarchical data sets effectively and efficiently. The challenge in developing these networks lies in the nonlinearity of the embedding space namely, the Hyperbolic space. Hyperbolic space is a homogeneous Riemannian manifold of the Lorentz group which is a semi-Riemannian manifold, i.e. a manifold equipped with an indefinite metric. Most existing methods (with some exceptions) use local linearization to define a variety of operations paralleling those used in traditional deep neural networks in Euclidean spaces. In this paper, we present a novel fully hyperbolic neural network which uses the concept of projections (embeddings) followed by an intrinsic aggregation and a nonlinearity all within the hyperbolic space. The novelty here lies in the projection which is designed to project data on to a lower-dimensional embedded hyperbolic space and hence leads to a nested hyperbolic space representation independently useful for dimensionality reduction. The main theoretical contribution is that the proposed embedding is proved to be isometric and equivariant under the Lorentz transformations, which are the natural isometric transformations in hyperbolic spaces. This projection is computationally efficient since it can be expressed by simple linear operations, and, due to the aforementioned equivariance property, it allows for weight sharing. The nested hyperbolic space representation is the core component of our network and therefore, we first compare this representation - independent of the network - with other dimensionality reduction methods such as tangent PCA, principal geodesic analysis (PGA) and HoroPCA. Based on this equivariant embedding, we develop a novel fully hyperbolic graph convolutional neural network architecture to learn the parameters of the projection. Finally, we present experiments demonstrating comparative performance of our network on several publicly available data sets.

Cite this paper

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

APA 7

Fan, X., Yang, C.-H., & Vemuri, B. C. (2022). Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2022, 356–365. https://doi.org/10.1109/cvpr52688.2022.00045

MLA 9

Fan, Xiran, et al. “Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, vol. 2022, 2022, pp. 356–365. https://doi.org/10.1109/cvpr52688.2022.00045.

Chicago

Fan, Xiran, Chun-Hao Yang, and Baba C. Vemuri. 2022. “Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings 2022: 356–365. https://doi.org/10.1109/cvpr52688.2022.00045.

Harvard

Fan, X., Yang, C.-H. and Vemuri, B. C. (2022) ‘Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2022, pp. 356–365. doi:10.1109/cvpr52688.2022.00045.

IEEE

X. Fan, C.-H. Yang, and B. C. Vemuri, “Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, vol. 2022, pp. 356–365, 2022, doi: 10.1109/cvpr52688.2022.00045.

BibTeX

@inproceedings{fan2022nested,
  title     = {{Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design}},
  author    = {Fan, Xiran and Yang, Chun-Hao and Vemuri, Baba C.},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
  year      = {2022},
  volume    = {2022},
  pages     = {356--365},
  doi       = {10.1109/cvpr52688.2022.00045},
  url       = {https://doi.org/10.1109/cvpr52688.2022.00045}
}

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

Citations by year

YearCitationsShare of the best year
202333
20241212
202566
202644

Its field-weighted citation impact is 1.43: it has been cited 1.43 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications

  • hyperbolic neural networks
  • dimensionality reduction
  • Lorentz transformation
  • isometric embedding
  • equivariance
  • parameter sharing
  • hyperbolic embeddings
  • principal geodesic analysis

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?

Fan, X., Yang, C.-H., & Vemuri, B. C. (2022). Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2022, 356–365. https://doi.org/10.1109/cvpr52688.2022.00045

How many times has this paper been cited?

25 times, according to OpenAlex on 20 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 PubMed Central: sign in and open the full text from this page.

Who wrote this paper?

Xiran Fan, Chun-Hao Yang, Baba C. Vemuri.

What is the DOI of this paper?

10.1109/cvpr52688.2022.00045, permanently at https://doi.org/10.1109/cvpr52688.2022.00045. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 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.