File Download
Links for fulltext
(May Require Subscription)
- Scopus: eid_2-s2.0-85090145803
- WOS: WOS:000534424308027
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Hyperbolic graph neural networks
Title | Hyperbolic graph neural networks |
---|---|
Authors | |
Issue Date | 2019 |
Publisher | Neural Information Processing Systems Foundation |
Citation | 3rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, 8-14 December 2019. In Advances in Neural Information Processing Systems, 2019, v. 32 How to Cite? |
Abstract | Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we propose a novel GNN architecture for learning representations on Riemannian manifolds with differentiable exponential and logarithmic maps. We develop a scalable algorithm for modeling the structural properties of graphs, comparing Euclidean and hyperbolic geometry. In our experiments, we show that hyperbolic GNNs can lead to substantial improvements on various benchmark datasets. |
Persistent Identifier | http://hdl.handle.net/10722/321896 |
ISSN | 2020 SCImago Journal Rankings: 1.399 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Qi | - |
dc.contributor.author | Nickel, Maximilian | - |
dc.contributor.author | Kiela, Douwe | - |
dc.date.accessioned | 2022-11-03T02:22:12Z | - |
dc.date.available | 2022-11-03T02:22:12Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | 3rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, 8-14 December 2019. In Advances in Neural Information Processing Systems, 2019, v. 32 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321896 | - |
dc.description.abstract | Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we propose a novel GNN architecture for learning representations on Riemannian manifolds with differentiable exponential and logarithmic maps. We develop a scalable algorithm for modeling the structural properties of graphs, comparing Euclidean and hyperbolic geometry. In our experiments, we show that hyperbolic GNNs can lead to substantial improvements on various benchmark datasets. | - |
dc.language | eng | - |
dc.publisher | Neural Information Processing Systems Foundation | - |
dc.relation.ispartof | Advances in Neural Information Processing Systems | - |
dc.title | Hyperbolic graph neural networks | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_OA_fulltext | - |
dc.identifier.scopus | eid_2-s2.0-85090145803 | - |
dc.identifier.volume | 32 | - |
dc.identifier.isi | WOS:000534424308027 | - |