Abstract
Interest has been growing lately towards learning representations for non-Euclidean geometric data structures. Such kinds of data are found everywhere ranging from social network graphs, brain images, sensor networks to 3-dimensional objects. To understand the underlying geometry and functions of these high dimensional discrete data with non-Euclidean structure, it requires their representations in non-Euclidean spaces. Recently, graph embedding in Riemannian spaces has been explored to successfully capture the geometric properties of networks and achieve the state-of-the-art quality in graph representation learning tasks. In this survey, we provide an overview on graph embeddings based on Riemannian geometry with different curvature spaces. We further present recent developments in various application areas using graph embedding models in non-Euclidean domains.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asta, D., Shalizi, C.R.: Geometric network comparison. arXiv preprint arXiv:1411.1350 (2014)
Bachmann, G., Bécigneul, G., Ganea, O.E.: Constant curvature graph convolutional networks. arXiv preprint arXiv:1911.05076 (2019)
Bakker, C., Halappanavar, M., Sathanur, A.V.: Dynamic graphs, community detection, and Riemannian geometry. Appl. Netw. Sci. 3(1), 3:1–3:30 (2018)
Balazevic, I., Allen, C., Hospedales, T.: Multi-relational poincaré graph embeddings. In: NIPS, pp. 4465–4475 (2019)
Berger, M., Gostiaux, B.: Differential Geometry: Manifolds, Curves, and Surfaces, vol. 115. Springer Science & Business Media, New York (2012). https://doi.org/10.1007/978-1-4612-1033-7
Boguná, M., Papadopoulos, F., Krioukov, D.: Sustaining the internet with hyperbolic mapping. Nat. Commun. 1(1), 1–8 (2010)
Bonnabel, S.: Stochastic gradient descent on Riemannian manifolds. IEEE Trans. Autom. Control 58(9), 2217–2229 (2013)
Bottou, L.: Stochastic gradient descent tricks. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 421–436. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_25
Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond Euclidean data. IEEE SPM 34(4), 18–42 (2017)
Chamberlain, B.P., Clough, J.R., Deisenroth, M.P.: Neural embeddings of graphs in hyperbolic space. arXiv preprint arXiv:1705.10359 (2017)
Chamberlain, B.P., Hardwick, S.R., Wardrope, D.R., Dzogang, F., Daolio, F., Vargas, S.: Scalable hyperbolic recommender systems. arXiv preprint arXiv:1902.08648 (2019)
Chami, I., Abu-El-Haija, S., Perozzi, B., Ré, C., Murphy, K.: Machine learning on graphs: A model and comprehensive taxonomy. arXiv preprint arXiv:2005.03675 (2020)
Chami, I., Wolf, A., Sala, F., Ré, C.: Low-dimensional knowledge graph embeddings via hyperbolic rotations. In: NIPS Workshop (2019)
Chami, I., Ying, Z., Ré, C., Leskovec, J.: Hyperbolic graph convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 4869–4880 (2019)
Davidson, T.R., Falorsi, L., De Cao, N., Kipf, T., Tomczak, J.M.: Hyperspherical variational auto-encoders. arXiv preprint arXiv:1804.00891 (2018)
Forman, R.: Bochner’s method for cell complexes and combinatorial Ricci curvature. Discrete Comput. Geom. 29(3), 323–374 (2003)
Ganea, O., Bécigneul, G., Hofmann, T.: Hyperbolic entailment cones for learning hierarchical embeddings. arXiv preprint arXiv:1804.01882 (2018)
Grattarola, D., Zambon, D., Livi, L., Alippi, C.: Change detection in graph streams by learning graph embeddings on constant-curvature manifolds. IEEE Trans. Neural Netw. Learn. Syst. 31(6), 1856–1869 (2019)
Gu, A., Sala, F., Gunel, B., Ré, C.: Learning mixed-curvature representations in product spaces. In: International Conference on Learning Representations (2018)
Gülçehre, Ç., et al.: Hyperbolic attention networks. arXiv preprint arXiv:1812.08434 abs/1805.09786 (2018)
Kolyvakis, P., Kalousis, A., Kiritsis, D.: Hyperkg: hyperbolic knowledge graph embeddings for knowledge base completion. arXiv preprint arXiv:1908.04895 (2019)
Krioukov, D.V., Papadopoulos, F., Kitsak, M., Vahdat, A., Boguñá, M.: Hyperbolic geometry of complex networks. Phys. Rev. E 82(3), 036106 (2010)
Le, M., Roller, S., Papaxanthos, L., Kiela, D., Nickel, M.: Inferring concept hierarchies from text corpora via hyperbolic embeddings. arXiv preprint arXiv:1902.00913 (2019)
Lee, J.M.: Riemannian Manifolds. GTM, vol. 176. Springer, New York (1997). https://doi.org/10.1007/b98852
Liu, Q., Nickel, M., Kiela, D.: Hyperbolic graph neural networks. In: NIPS, pp. 8230–8241 (2019)
Najman, L., Romon, P. (eds.): Modern Approaches to Discrete Curvature. LNM, vol. 2184. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58002-9
Ni, C., Lin, Y., Luo, F., Gao, J.: Community detection on networks with Ricci flow. Sci. Rep. 9(1), 1–12 (2019)
Nickel, M., Kiela, D.: Poincaré embeddings for learning hierarchical representations. In: Advances in Neural Information Processing Systems, pp. 6338–6347 (2017)
Nickel, M., Kiela, D.: Learning continuous hierarchies in the Lorentz model of hyperbolic geometry. arXiv preprint arXiv:1806.03417 (2018)
Ollivier, Y.: Ricci curvature of Markov chains on metric spaces. J. Funct. Anal. 256(3), 810–864 (2009)
Papadis, N., Stai, E., Karyotis, V.: A path-based recommendations approach for online systems via hyperbolic network embedding. In: IEEE. ISCC, pp. 973–980 (2017)
Pei, H., Wei, B., Chang, K.C., Lei, Y., Yang, B.: Geom-GCN: geometric graph convolutional networks. In: ICLR. OpenReview.net (2020)
Sala, F., Sa, C.D., Gu, A., Ré, C.: Representation tradeoffs for hyperbolic embeddings. In: ICML, pp. 4457–4466 (2018)
Samal, A., Sreejith, R., Gu, J., Liu, S., Saucan, E., Jost, J.: Comparative analysis of two discretizations of Ricci curvature for complex networks. Sci. Rep. 8(1), 1–16 (2018)
Shavitt, Y., Tankel, T.: Hyperbolic embedding of internet graph for distance estimation and overlay construction. IEEE/ACM Trans. Netw. 16(1), 25–36 (2008)
Shimizu, R., Mukuta, Y., Harada, T.: Hyperbolic neural networks++. arXiv preprint arXiv:2006.08210 (2020)
Sun, Z., Deng, Z., Nie, J., Tang, J.: Rotate: knowledge graph embedding by relational rotation in complex space. CoRR abs/1902.10197 (2019)
Suzuki, R., Takahama, R., Onoda, S.: Hyperbolic disk embeddings for directed acyclic graphs. In: ICML, pp. 6066–6075 (2019)
Tifrea, A., Bécigneul, G., Ganea, O.: Poincaré glove: hyperbolic word embeddings. CoRR abs/1810.06546 (2018)
Tran, L.V., Tay, Y., Zhang, S., Cong, G., Li, X.: HyperML: a boosting metric learning approach in hyperbolic space for recommender systems. In: WSDM (2020)
Verbeek, K., Suri, S.: Metric embedding, hyperbolic space, and social networks. In: Proceedings of the Thirtieth Annual Symposium on Computational Geometry, pp. 501–510 (2014)
Wang, X., Zhang, Y., Shi, C.: Hyperbolic heterogeneous information network embedding. AAAI 33, 5337–5344 (2019)
Xu, D., Ruan, C., Korpeoglu, E., Kumar, S., Achan, K.: Product knowledge graph embedding for e-commerce. In: Web Search and Data Mining, pp. 672–680 (2020)
Ye, Z., Liu, K.S., Ma, T., Gao, J., Chen, C.: Curvature graph network. In: 8th International Conference on Learning Representations, ICLR. OpenReview.net (2020)
Zhang, Y., Wang, X., Jiang, X., Shi, C., Ye, Y.: Hyperbolic graph attention network. arXiv preprint arXiv:1912.03046 (2019)
Acknowledgements
The work described in this paper was supported by the Research Grants Council of the Hong Kong Special Administrative Region, China (CUHK 2410021, Research Impact Fund, No. R5034-18).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Saxena, C., Liu, T., King, I. (2020). A Survey of Graph Curvature and Embedding in Non-Euclidean Spaces. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science(), vol 12533. Springer, Cham. https://doi.org/10.1007/978-3-030-63833-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-63833-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63832-0
Online ISBN: 978-3-030-63833-7
eBook Packages: Computer ScienceComputer Science (R0)