The DOI matches its Crossref record; 29 of the 33 references it cites were found in a registry or an index.
Low-Dimensional Hyperbolic Knowledge Graph Embeddings
Open accessAbstract
Knowledge graph (KG) embeddings learn lowdimensional representations of entities and relations to predict missing facts.KGs often exhibit hierarchical and logical patterns which must be preserved in the embedding space.For hierarchical data, hyperbolic embedding methods have shown promise for high-fidelity and parsimonious representations.However, existing hyperbolic embedding methods do not account for the rich logical patterns in KGs.In this work, we introduce a class of hyperbolic KG embedding models that simultaneously capture hierarchical and logical patterns.Our approach combines hyperbolic reflections and rotations with attention to model complex relational patterns.Experimental results on standard KG benchmarks show that our method improves over previous Euclidean-and hyperbolic-based efforts by up to 6.1% in mean reciprocal rank (MRR) in low dimensions.Furthermore, we observe that different geometric transformations capture different types of relations while attentionbased transformations generalize to multiple relations.In high dimensions, our approach yields new state-of-the-art MRRs of 49.6% on WN18RR and 57.7% on YAGO3-10.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source doesn’t support the claim as written.
In the citing paper
“While there are methods for reasoning over KGs that use hyperbolic space (MuRP [15], RotH [16]), which is suitable for modeling tree-like graphs, the choice of relational transformations used in these works (rotation) prevents them from faithfully capturing all the properties of hierarchical relations.”
From Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones (2021) · cites this paper as [16]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, transformations used in MuRP and RotH cannot capture transitive relations which hierarchical relations naturally are.”
From Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones (2021) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“RotH [16] uses rotation and reflection transformation in n -dimensional Poincaré space to model relational patterns, and achieves state-of-the-art for the KG completion task, especially under low-dimensionality.”
From Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones (2021) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The reason why RotH [16] needs learning space curvature while ConE does not lie in the choice of embedding space: RotH uses a 2 d -dimensional hyperbolic space while ConE uses product space of d hyperbolic planes.”
From Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones (2021) · cites this paper as [16]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
WordNet: a lexical database for English
Miller, G. A. (1995) · Communications of the ACM · doi:10.1145/219717.219748 · Cited by 14,015
(2010) · Cited by 8,261
Modeling Relational Data with Graph Convolutional Networks
Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., & Welling, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-93417-4_38 · Cited by 5,570
Knowledge Graph Embedding by Translating on Hyperplanes
Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8870 · Cited by 3,915
Learning Entity and Relation Embeddings for Knowledge Graph Completion
Lin, Y., Liu, Z., Sun, M., Liu, Y., & Zhu, X. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9491 · Cited by 3,749
Yago: a core of semantic knowledge
Suchanek, F. M., Kasneci, G., & Weikum, G. (2007) · Proceedings of the 16th international conference on World Wide Web · doi:10.1145/1242572.1242667 · Cited by 2,512
Embedding Entities and Relations for Learning and Inference in Knowledge Bases
Yang, B., Yih, W.-T., He, X., Gao, J., & Deng, L. (2014) · arXiv · doi:10.48550/arxiv.1412.6575 · Cited by 2,252
Complex Embeddings for Simple Link Prediction
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., & Bouchard, G. (2016) · arXiv · doi:10.48550/arxiv.1606.06357 · Cited by 2,100
Knowledge Graph Embedding via Dynamic Mapping Matrix
Ji, G., He, S., Xu, L., Liu, K., & Zhao, J. (2015) · Annual Meeting of the Association for Computational Linguistics · doi:10.3115/v1/p15-1067 · Cited by 1,943
Research works printed but not linked: 4
- Ivana Balažević, Carl Allen, and Timothy Hospedales. 2019. Multi-relational poincaré graph embeddings. In Advances in Neural Information Processing Sys- tems, pages 4465-4475.
- Ivana Balazevic, Carl Allen, and Timothy Hospedales. 2019. Tucker: Tensor factorization for knowledge graph completion. In Proceedings of the 2019 Con- ference on Empirical Methods in Natural Language Processing and the 9th International Joint Confer- ence on Natural Language Processing (EMNLP- IJCNLP), pages 5188-5197.
- Antoine Bordes, Nicolas Usunier, Alberto Garcia- Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi- relational data. In Advances in Neural Information Processing Systems, pages 2787-2795.
- Octavian Ganea, Gary Bécigneul, and Thomas Hof- mann. 2018. Hyperbolic neural networks. In Ad- vances in Neural Information Processing Systems.
Cited by
Sorted by citations
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications
Ji, S., Pan, S., Cambria, E., Marttinen, P., & Yu, P. S. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3070843 · Cited by 2,947
Benchmarking Graph Neural NetworksPreprint
Dwivedi, V. P., Joshi, C. K., Luu, A. T., Laurent, T., Bengio, Y., & Bresson, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00982 · Cited by 886
A Generalization of Transformer Networks to Graphs
Dwivedi, V. P., & Bresson, X. (2020) · arXiv · doi:10.48550/arxiv.2012.09699 · Cited by 398
Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion
Wang, B., Shen, T., Long, G., Zhou, T., Wang, Y., & Chang, Y. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3450043 · Cited by 297
Hyperbolic Deep Neural Networks: A Survey
Peng, W., Varanka, T., Mostafa, A., Shi, H., & Zhao, G. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3136921 · Cited by 252
Metadata
- Authors
- Chami, I., Wolf, A., Juan, D.-C., Sala, F., Ravi, S., & Ré, C.
- Affiliations
- Stanford University (US)
- Google (United States) (US)
- ORCID
- Ré, Christopher
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 6901-6914
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W3023009950
- Cited by
- 384
- References
- 33
- Citations by year
- 2026: 26 · 2025: 55 · 2024: 87 · 2023: 78 · 2022: 59 · 2021: 69 · 2020: 10
- FWCI
- 20.63
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1763315, 1563078, 1937301)
- Gordon and Betty Moore Foundation
- Accenture
- VMware
- Okawa Foundation for Information and Telecommunications
- Swiss Re
- Ant Financial Services Group
- National Institutes of Health (N000141712266)
- Defense Advanced Research Projects Agency (FA86501827882, FA86501827865)
- Office of Naval Research (N000141712266)
- National Institute of Biomedical Imaging and Bioengineering (U54EB020405)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- knowledge graph embedding, hyperbolic embeddings, hyperbolic geometry, hyperbolic reflections, hyperbolic rotations, attention mechanism, hierarchical relations, logical relations, low-dimensional representation, missing fact prediction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
