Shadow Cones: A Generalized Framework for Partial Order Embeddings
Abstract: Hyperbolic space has proven to be well-suited for capturing hierarchical relations in data, such as trees and directed acyclic graphs. Prior work introduced the concept of entailment cones, which uses partial orders defined by nested cones in the Poincar\'e ball to model hierarchies. Here, we introduce the ``shadow cones" framework, a physics-inspired entailment cone construction. Specifically, we model partial orders as subset relations between shadows formed by a light source and opaque objects in hyperbolic space. The shadow cones framework generalizes entailment cones to a broad class of formulations and hyperbolic space models beyond the Poincar\'e ball. This results in clear advantages over existing constructions: for example, shadow cones possess better optimization properties over constructions limited to the Poincar\'e ball. Our experiments on datasets of various sizes and hierarchical structures show that shadow cones consistently and significantly outperform existing entailment cone constructions. These results indicate that shadow cones are an effective way to model partial orders in hyperbolic space, offering physically intuitive and novel insights about the nature of such structures.
- The transitive reduction of a directed graph. SIAM Journal on Computing, 1(2):131–137, 1972.
- James W Anderson. Hyperbolic geometry. Springer Science & Business Media, 2006.
- Modeling heterogeneous hierarchies with relation-specific hyperbolic cones. Advances in Neural Information Processing Systems, 34:12316–12327, 2021.
- Multi-relational poincaré graph embeddings. Advances in Neural Information Processing Systems, 32, 2019.
- Capacity and bias of learned geometric embeddings for directed graphs. Advances in Neural Information Processing Systems, 34:16423–16436, 2021.
- Geometric deep learning: going beyond euclidean data. CoRR, abs/1611.08097, 2016. URL http://arxiv.org/abs/1611.08097.
- Low-dimensional hyperbolic knowledge graph embeddings. arXiv preprint arXiv:2005.00545, 2020.
- Fellbaum Christiane. Wordnet: an electronic lexical database. Computational Linguistics, pp. 292–296, 1998.
- Hyperbolic entailment cones for learning hierarchical embeddings. In International Conference on Machine Learning, pp. 1646–1655. PMLR, 2018.
- Marti A Hearst. Automatic acquisition of hyponyms from large text corpora. In COLING 1992 Volume 2: The 14th International Conference on Computational Linguistics, 1992.
- Shyuichi Izumiya. Horospherical geometry in the hyperbolic space. In Noncommutativity and Singularities: Proceedings of French–Japanese symposia held at IHÉS in 2006, volume 55, pp. 31–50. Mathematical Society of Japan, 2009.
- Inferring concept hierarchies from text corpora via hyperbolic embeddings. arXiv preprint arXiv:1902.00913, 2019.
- Deep hierarchical semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1246–1257, 2022.
- Improved representation learning for predicting commonsense ontologies. arXiv preprint arXiv:1708.00549, 2017.
- Distributed representations of words and phrases and their compositionality, 2013.
- Poincaré embeddings for learning hierarchical representations. Advances in neural information processing systems, 30, 2017.
- Learning continuous hierarchies in the lorentz model of hyperbolic geometry. In International conference on machine learning, pp. 3779–3788. PMLR, 2018.
- GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543, Doha, Qatar, October 2014. Association for Computational Linguistics. doi: 10.3115/v1/D14-1162. URL https://aclanthology.org/D14-1162.
- Representation tradeoffs for hyperbolic embeddings. In International conference on machine learning, pp. 4460–4469. PMLR, 2018.
- Rik Sarkar. Low distortion delaunay embedding of trees in hyperbolic plane. In Graph Drawing: 19th International Symposium, GD 2011, Eindhoven, The Netherlands, September 21-23, 2011, Revised Selected Papers 19, pp. 355–366. Springer, 2012.
- Poincar\\\backslash\’e glove: Hyperbolic word embeddings. arXiv preprint arXiv:1810.06546, 2018.
- Coneheads: Hierarchy aware attention. arXiv preprint, 2023.
- Order-embeddings of images and language. arXiv preprint arXiv:1511.06361, 2015.
- An inference approach to basic level of categorization. In Proceedings of the 24th acm international on conference on information and knowledge management, pp. 653–662, 2015.
- Probase: A probabilistic taxonomy for text understanding. In Proceedings of the 2012 ACM SIGMOD international conference on management of data, pp. 481–492, 2012.
- Random laplacian features for learning with hyperbolic space. In International Conference on Learning Representations, 2023.
- Numerically accurate hyperbolic embeddings using tiling-based models. Advances in Neural Information Processing Systems, 32, 2019.
- Representing hyperbolic space accurately using multi-component floats. Advances in Neural Information Processing Systems, 34:15570–15581, 2021.
- Htorch: Pytorch-based robust optimization in hyperbolic space. GitHub Repository, 2023. URL https://github.com/ydtydr/HTorch.
- Modeling transitivity and cyclicity in directed graphs via binary code box embeddings. Advances in Neural Information Processing Systems, 35:10587–10599, 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.