Conference paper · 2021 · Open access

A Hyperbolic-to-Hyperbolic Graph Convolutional Network

Jindou Dai, Yuwei Wu, Zhi Feng Gao, Yunde Jia

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 154–163 · Published 1 June 2021 · DOI 10.1109/cvpr46437.2021.00022

Open PDFView at the publisherCite this paper

In brief

“A Hyperbolic-to-Hyperbolic Graph Convolutional Network” is a 2021 conference paper by Jindou Dai and 3 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 135 citations as of 22 November 2026, which puts it in the top 3% of works published in 2021 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
135
Most cited in
2025 (34)
Field-weighted impact
5.05
References
53
Authors
4

Abstract

Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hyperbolic manifolds, which is inferior because tangent space is only a local approximation of a manifold. In this paper, we propose a hyperbolic-to-hyperbolic graph convolutional network (H2H-GCN) that directly works on hyperbolic manifolds. Specifically, we developed a manifold-preserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic neighborhood aggregation. The hyperbolic feature transformation works as linear transformation on hyperbolic manifolds. It ensures the transformed node representations still lie on the hyperbolic manifold by imposing the orthogonal constraint on the transformation sub-matrix. The hyperbolic neighborhood aggregation updates each node representation via the Einstein midpoint. The H2H-GCN avoids the distortion caused by tangent space approximations and keeps the global hyperbolic structure. Extensive experiments show that the H2H-GCN achieves substantial improvements on the link prediction, node classification, and graph classification tasks.

Cite this paper

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

APA 7

Dai, J., Wu, Y., Gao, Z. F., & Jia, Y. (2021). A Hyperbolic-to-Hyperbolic Graph Convolutional Network. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 154–163. https://doi.org/10.1109/cvpr46437.2021.00022

MLA 9

Dai, Jindou, et al. “A Hyperbolic-to-Hyperbolic Graph Convolutional Network.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2021, pp. 154–163. https://doi.org/10.1109/cvpr46437.2021.00022.

Chicago

Dai, Jindou, Yuwei Wu, Zhi Feng Gao, and Yunde Jia. 2021. “A Hyperbolic-to-Hyperbolic Graph Convolutional Network.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings: 154–163. https://doi.org/10.1109/cvpr46437.2021.00022.

Harvard

Dai, J. et al. (2021) ‘A Hyperbolic-to-Hyperbolic Graph Convolutional Network’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 154–163. doi:10.1109/cvpr46437.2021.00022.

IEEE

J. Dai, Y. Wu, Z. F. Gao, and Y. Jia, “A Hyperbolic-to-Hyperbolic Graph Convolutional Network,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 154–163, 2021, doi: 10.1109/cvpr46437.2021.00022.

BibTeX

@inproceedings{dai2021hyperbolic,
  title     = {{A Hyperbolic-to-Hyperbolic Graph Convolutional Network}},
  author    = {Dai, Jindou and Wu, Yuwei and Gao, Zhi Feng and Jia, Yunde},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
  year      = {2021},
  pages     = {154--163},
  doi       = {10.1109/cvpr46437.2021.00022},
  url       = {https://doi.org/10.1109/cvpr46437.2021.00022}
}

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

Citations by year

YearCitationsShare of the best year
202155
20221313
20232222
20242929
20253434
20263232

Its field-weighted citation impact is 5.05: it has been cited 5.05 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 › Advanced Graph Neural Networks

  • hyperbolic manifolds
  • orthogonality constraints
  • hierarchical graphs
  • link prediction
  • node classification
  • graph classification

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?

Dai, J., Wu, Y., Gao, Z. F., & Jia, Y. (2021). A Hyperbolic-to-Hyperbolic Graph Convolutional Network. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 154–163. https://doi.org/10.1109/cvpr46437.2021.00022

How many times has this paper been cited?

135 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?

Jindou Dai, Yuwei Wu, Zhi Feng Gao, Yunde Jia.

What is the DOI of this paper?

10.1109/cvpr46437.2021.00022, permanently at https://doi.org/10.1109/cvpr46437.2021.00022. 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.