Abstract
The Gromov-Wasserstein (GW) framework adapts ideas from optimal transport to allow for the comparison of probability distributions defined on different metric spaces. Scalable computation of GW distances and associated matchings on graphs and point clouds have recently been made possible by state-of-the-art algorithms such as S-GWL and MREC. Each of these algorithmic breakthroughs relies on decomposing the underlying spaces into parts and performing matchings on these parts, adding recursion as needed. While very successful in practice, theoretical guarantees on such methods are limited. Inspired by recent advances in the theory of quantization for metric measure spaces, we define Quantized Gromov Wasserstein (qGW): a metric that treats parts as fundamental objects and fits into a hierarchy of theoretical upper bounds for the GW problem. This formulation motivates a new algorithm for approximating optimal GW matchings which yields algorithmic speedups and reductions in memory complexity. Consequently, we are able to go beyond outperforming state-of-the-art and apply GW matching at scales that are an order of magnitude larger than in the existing literature, including datasets containing over 1M points.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alvarez-Melis, D., Jaakkola, T.: Gromov-Wasserstein alignment of word embedding spaces. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 1881–1890 (2018)
Armeni, I., et al.: 3D semantic parsing of large-scale indoor spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1534–1543 (2016)
Blumberg, A.J., Carriere, M., Mandell, M.A., Rabadan, R., Villar, S.: MREC: a fast and versatile framework for aligning and matching point clouds with applications to single cell molecular data. arXiv preprint arXiv:2001.01666 (2020)
Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. Comput. Netw. ISDN Syst. 30(1–7), 107–117 (1998)
Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Numerical Geometry of Non-Rigid Shapes. MCS, Springer, New York (2009). https://doi.org/10.1007/978-0-387-73301-2
Bunne, C., Alvarez-Melis, D., Krause, A., Jegelka, S.: Learning generative models across incomparable spaces. In: International Conference on Machine Learning, pp. 851–861 (2019)
Chowdhury, S., Mémoli, F.: The Gromov-Wasserstein distance between networks and stable network invariants. Inf. Inference J. IMA 8(4), 757–787 (2019)
Chowdhury, S., Needham, T.: Gromov-Wasserstein averaging in a Riemannian framework. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 842–843 (2020)
Chowdhury, S., Needham, T.: Generalized spectral clustering via Gromov-Wasserstein learning. In: International Conference on Artificial Intelligence and Statistics, pp. 712–720. PMLR (2021)
Demetci, P., Santorella, R., Sandstede, B., Noble, W.S., Singh, R.: Gromov-Wasserstein optimal transport to align single-cell multi-omics data. BioRxiv (2020)
Fatras, K., Zine, Y., Majewski, S., Flamary, R., Gribonval, R., Courty, N.: Minibatch optimal transport distances; analysis and applications. arXiv preprint arXiv:2101.01792 (2021)
Flamary, R., Courty, N.: POT Python Optimal Transport library (2017). https://pythonot.github.io/
Garg, V., Jaakkola, T.: Solving graph compression via optimal transport. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Hagberg, A., Swart, P., Chult, D.S.: Exploring network structure, dynamics, and function using NetworkX. Technical report, Los Alamos National Lab. (LANL), Los Alamos, NM (United States) (2008)
Mémoli, F.: On the use of Gromov-Hausdorff distances for shape comparison. The Eurographics Association (2007)
Mémoli, F.: Gromov-Hausdorff distances in Euclidean spaces. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008)
Mémoli, F.: Gromov-Wasserstein distances and the metric approach to object matching. Found. Comput. Math. 11(4), 417–487 (2011)
Mémoli, F., Needham, T.: Gromov-Monge quasi-metrics and distance distributions. arXiv preprint arXiv:1810.09646 (2018)
Mémoli, F., Sapiro, G.: Comparing point clouds. In: SGP 2004: Proceedings of the 2004 Eurographics/ACM SIGGRAPH symposium on Geometry Processing, pp. 32–40. ACM, New York (2004). https://doi.org/http://doi.acm.org/10.1145/1057432.1057436
Mémoli, F., Sapiro, G.: A theoretical and computational framework for isometry invariant recognition of point cloud data. Found. Comput. Math. 5(3), 313–347 (2005)
Mémoli, F., Sidiropoulos, A., Singhal, K.: Sketching and clustering metric measure spaces. arXiv preprint arXiv:1801.00551 (2018)
Mérigot, Q.: A multiscale approach to optimal transport. In: Computer Graphics Forum, vol. 30, pp. 1583–1592. Wiley Online Library (2011)
Papadakis, P.: The canonically posed 3D objects dataset. In: Eurographics Workshop on 3D Object Retrieval, pp. 33–36 (2014)
Parés, F., et al.: Fluid communities: a competitive, scalable and diverse community detection algorithm. In: Cherifi, C., Cherifi, H., Karsai, M., Musolesi, M. (eds.) COMPLEX NETWORKS 2017 2017. SCI, vol. 689, pp. 229–240. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-72150-7_19
Peyré, G., Cuturi, M., Solomon, J.: Gromov-Wasserstein averaging of kernel and distance matrices. In: International Conference on Machine Learning (2016)
Peyré, G., Cuturi, M., et al.: Computational optimal transport: with applications to data science. Found. Trends® Mach. Learn. 11(5–6), 355–607 (2019)
Sato, R., Cuturi, M., Yamada, M., Kashima, H.: Fast and robust comparison of probability measures in heterogeneous spaces. arXiv:2002.01615 (2020)
Séjourné, T., Vialard, F.X., Peyré, G.: The unbalanced Gromov Wasserstein distance: conic formulation and relaxation. arXiv preprint arXiv:2009.04266 (2020)
Solomon, J., Peyré, G., Kim, V.G., Sra, S.: Entropic metric alignment for correspondence problems. ACM Trans. Graph. (TOG) 35(4), 1–13 (2016)
Sturm, K.T.: The space of spaces: curvature bounds and gradient flows on the space of metric measure spaces. arXiv preprint arXiv:1208.0434 (2012)
Sturm, K.T., et al.: On the geometry of metric measure spaces. Acta Math. 196(1), 65–131 (2006)
Vayer, T., Courty, N., Tavenard, R., Flamary, R.: Optimal transport for structured data with application on graphs. In: International Conference on Machine Learning, pp. 6275–6284 (2019)
Vayer, T., Flamary, R., Tavenard, R., Chapel, L., Courty, N.: Sliced Gromov-Wasserstein. In: NeurIPS 2019-Thirty-third Conference on Neural Information Processing Systems, vol. 32 (2019)
Villani, C.: Topics in optimal transportation. American Mathematical Soc. (2003)
Weitkamp, C.A., Proksch, K., Tameling, C., Munk, A.: Gromov-Wasserstein distance based object matching: asymptotic inference. arXiv:2006.12287 (2020)
Xu, H., Luo, D., Carin, L.: Scalable Gromov-Wasserstein learning for graph partitioning and matching. In: Advances in Neural Information Processing Systems (2019)
Xu, H., Luo, D., Zha, H., Carin, L.: Gromov-Wasserstein learning for graph matching and node embedding. In: International Conference on Machine Learning (2019)
Acknowledgements
We would like to thank Mathieu Carrière for help with the MREC code, Vikas Garg for sharing code from [13], Facundo Mémoli for providing useful feedback, and the anonymous reviewers for helpful comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chowdhury, S., Miller, D., Needham, T. (2021). Quantized Gromov-Wasserstein. In: Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2021. Lecture Notes in Computer Science(), vol 12977. Springer, Cham. https://doi.org/10.1007/978-3-030-86523-8_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-86523-8_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86522-1
Online ISBN: 978-3-030-86523-8
eBook Packages: Computer ScienceComputer Science (R0)
