Conference paper · 2025 · Open access
Hyperbolic Deep Learning for Foundation Models: A Survey
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 6021–6031 · Published 3 August 2025 · DOI 10.1145/3711896.3736564
In brief
“Hyperbolic Deep Learning for Foundation Models: A Survey” is a 2025 conference paper by Neil He and 4 co-authors, published in ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD). OpenAlex counts 28 citations as of 18 November 2026, which puts it in the top 1% of works published in 2025 by citations. It is open access under a CC BY-NC-SA licence: the full text is free to read at ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).
- Citations
- 28
- Most cited in
- 2026 (25)
- Field-weighted impact
- 4.93
- References
- 112
- Authors
- 5
Abstract
Foundation models pre-trained on massive datasets, including large language models (LLMs), vision-language models (VLMs), and large multimodal models, have demonstrated remarkable success in diverse downstream tasks. However, recent studies have shown fundamental limitations of these models: (1) limited representational capacity(2) lower adaptability, and (3) diminishing scalability. These shortcomings raise a critical question: is Euclidean geometry truly the optimal inductive bias for all foundation models, or could incorporating alternative geometric spaces enable models to better align with the intrinsic structure of real-world data and improve reasoning processes? Hyperbolic spaces, a class of non-Euclidean manifolds characterized by exponential volume growth with respect to distance, offer a mathematically grounded solution. These spaces enable low-distortion embeddings of hierarchical structures (e.g., trees, taxonomies) and power-law distributions with substantially fewer dimensions compared to Euclidean counterparts. Recent advances have leveraged these properties to enhance foundation models, including improving LLMs' complex reasoning ability, VLMs' zero-shot generalization, and cross-modal semantic alignment, while maintaining parameter efficiency. This paper provides a comprehensive review of hyperbolic neural networks and their recent development for foundation models. We further outline key challenges and research directions to advance the field.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
He, N., Madhu, H., Bui, N., Yang, M., & Ying, R. (2025). Hyperbolic Deep Learning for Foundation Models: A Survey. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 6021–6031. https://doi.org/10.1145/3711896.3736564
MLA 9
He, Neil, et al. “Hyperbolic Deep Learning for Foundation Models: A Survey.” ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025, pp. 6021–6031. https://doi.org/10.1145/3711896.3736564.
Chicago
He, Neil, Hiren Madhu, Ngoc Bui, Menglin Yang, and Rex Ying. 2025. “Hyperbolic Deep Learning for Foundation Models: A Survey.” ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD): 6021–6031. https://doi.org/10.1145/3711896.3736564.
Harvard
He, N. et al. (2025) ‘Hyperbolic Deep Learning for Foundation Models: A Survey’, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 6021–6031. doi:10.1145/3711896.3736564.
IEEE
N. He, H. Madhu, N. Bui, M. Yang, and R. Ying, “Hyperbolic Deep Learning for Foundation Models: A Survey,” ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 6021–6031, 2025, doi: 10.1145/3711896.3736564.
BibTeX
@inproceedings{he2025hyperbolic,
title = {{Hyperbolic Deep Learning for Foundation Models: A Survey}},
author = {He, Neil and Madhu, Hiren and Bui, Ngoc and Yang, Menglin and Ying, Rex},
booktitle = {ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
year = {2025},
pages = {6021--6031},
doi = {10.1145/3711896.3736564},
url = {https://doi.org/10.1145/3711896.3736564}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- hyperbolic neural networks
- hyperbolic geometry
- foundation models
- large language models
- vision-language models
- large multimodal models
- inductive bias
- hierarchical data structures
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?
He, N., Madhu, H., Bui, N., Yang, M., & Ying, R. (2025). Hyperbolic Deep Learning for Foundation Models: A Survey. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 6021–6031. https://doi.org/10.1145/3711896.3736564
How many times has this paper been cited?
28 times, according to OpenAlex on 18 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 ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD): sign in and open the PDF from this page.
Who wrote this paper?
Neil He, Hiren Madhu, Ngoc Bui, Menglin Yang, Rex Ying.
What is the DOI of this paper?
10.1145/3711896.3736564, permanently at https://doi.org/10.1145/3711896.3736564. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 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.