Paper · 2019 · Open access
Hyperbolic Graph Convolutional Neural Networks
PubMed, 32, 4869–4880 · Published 28 October 2019 · DOI 10.48550/arxiv.1910.12933
In brief
“Hyperbolic Graph Convolutional Neural Networks” is a 2019 paper by Ines Chami and 3 co-authors, published in PubMed. OpenAlex counts 971 citations as of 19 November 2026, which puts it in the top 4% of works published in 2019 by citations. It is open access: the full text is free to read at PubMed Central.
- Citations
- 971
- Most cited in
- 2026 (203)
- Field-weighted impact
- 29.38
- References
- 52
- Authors
- 4
Abstract
Graph convolutional neural networks (GCNs) embed nodes in a graph into Euclidean space, which has been shown to incur a large distortion when embedding real-world graphs with scale-free or hierarchical structure. Hyperbolic geometry offers an exciting alternative, as it enables embeddings with much smaller distortion. However, extending GCNs to hyperbolic geometry presents several unique challenges because it is not clear how to define neural network operations, such as feature transformation and aggregation, in hyperbolic space. Furthermore, since input features are often Euclidean, it is unclear how to transform the features into hyperbolic embeddings with the right amount of curvature. Here we propose Hyperbolic Graph Convolutional Neural Network (HGCN), the first inductive hyperbolic GCN that leverages both the expressiveness of GCNs and hyperbolic geometry to learn inductive node representations for hierarchical and scale-free graphs. We derive GCNs operations in the hyperboloid model of hyperbolic space and map Euclidean input features to embeddings in hyperbolic spaces with different trainable curvature at each layer. Experiments demonstrate that HGCN learns embeddings that preserve hierarchical structure, and leads to improved performance when compared to Euclidean analogs, even with very low dimensional embeddings: compared to state-of-the-art GCNs, HGCN achieves an error reduction of up to 63.1% in ROC AUC for link prediction and of up to 47.5% in F1 score for node classification, also improving state-of-the art on the Pubmed dataset.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chami, I., Ying, R., Ré, C., & Leskovec, J. (2019). Hyperbolic Graph Convolutional Neural Networks. PubMed, 32, 4869–4880. https://doi.org/10.48550/arxiv.1910.12933
MLA 9
Chami, Ines, et al. “Hyperbolic Graph Convolutional Neural Networks.” PubMed, vol. 32, 2019, pp. 4869–4880. https://doi.org/10.48550/arxiv.1910.12933.
Chicago
Chami, Ines, Rex Ying, Christopher Ré, and Jure Leskovec. 2019. “Hyperbolic Graph Convolutional Neural Networks.” PubMed 32: 4869–4880. https://doi.org/10.48550/arxiv.1910.12933.
Harvard
Chami, I. et al. (2019) ‘Hyperbolic Graph Convolutional Neural Networks’, PubMed, 32, pp. 4869–4880. doi:10.48550/arxiv.1910.12933.
IEEE
I. Chami, R. Ying, C. Ré, and J. Leskovec, “Hyperbolic Graph Convolutional Neural Networks,” PubMed, vol. 32, pp. 4869–4880, 2019, doi: 10.48550/arxiv.1910.12933.
BibTeX
@article{chami2019hyperbolic,
title = {{Hyperbolic Graph Convolutional Neural Networks}},
author = {Chami, Ines and Ying, Rex and Ré, Christopher and Leskovec, Jure},
journal = {PubMed},
year = {2019},
volume = {32},
pages = {4869--4880},
doi = {10.48550/arxiv.1910.12933},
url = {https://doi.org/10.48550/arxiv.1910.12933}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2019 | 4 | |
| 2020 | 46 | |
| 2021 | 147 | |
| 2022 | 129 | |
| 2023 | 141 | |
| 2024 | 131 | |
| 2025 | 170 | |
| 2026 | 203 |
Its field-weighted citation impact is 29.38: it has been cited 29.38 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 geometry
- hyperbolic embeddings
- hyperboloid model
- scale-free networks
- hierarchical graphs
- link prediction
- node classification
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Chami, I., Ying, R., Ré, C., & Leskovec, J. (2019). Hyperbolic Graph Convolutional Neural Networks. PubMed, 32, 4869–4880. https://doi.org/10.48550/arxiv.1910.12933
How many times has this paper been cited?
971 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 PubMed Central: sign in and open the full text from this page.
Who wrote this paper?
Ines Chami, Rex Ying, Christopher Ré, Jure Leskovec.
What is the DOI of this paper?
10.48550/arxiv.1910.12933, permanently at https://doi.org/10.48550/arxiv.1910.12933. 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.