The Ultrametric Gromov-Wasserstein Distance

被引:1
|
作者
Memoli, Facundo [1 ]
Munk, Axel [2 ]
Wan, Zhengchao [3 ]
Weitkamp, Christoph [2 ]
机构
[1] Ohio State Univ, Dept Math, Columbus, OH 43210 USA
[2] Univ Gottingen, Inst Math Stochast, Gottingen, Germany
[3] Univ Calif San Diego, Halicioglu Data Sci Inst, La Jolla, CA USA
关键词
Ultrametric space; Gromov-Hausdorff distance; Gromov-Wasserstein distance; Optimal transport; METRIC-SPACES; GEOMETRY; REPRESENTATION; SIMILARITY; ALIGNMENT; OBJECTS;
D O I
10.1007/s00454-023-00583-0
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
We investigate compact ultrametric measure spaces which form a subset U(w )of the collection of all metric measure spaces M-w. In analogy with the notion of the ultrametric Gromov-Hausdorff distance on the collection of ultrametric spaces , we define ultrametric versions of two metrics on U-w, namely of Sturm's Gromov-Wasserstein distance of order p and of the Gromov-Wasserstein distance of order p. We study the basic topological and geometric properties of these distances as well as their relation and derive for p = infinity a polynomial time algorithm for their calculation. Further, several lower bounds for both distances are derived and some of our results are generalized to the case of finite ultra-dissimilarity spaces. Finally, we study the relation between the Gromov-Wasserstein distance and its ultrametric version (as well as the relation between the corresponding lower bounds) in simulations and apply our findings for phylogenetic tree shape comparisons.
引用
收藏
页码:1378 / 1450
页数:73
相关论文
共 50 条
  • [21] Gromov-Wasserstein Factorization Models for Graph Clustering
    Xu, Hongteng
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 6478 - 6485
  • [22] Comparison results for Gromov-Wasserstein and Gromov-Monge distances
    Memoli, Facundo
    Needham, Tom
    ESAIM-CONTROL OPTIMISATION AND CALCULUS OF VARIATIONS, 2024, 30
  • [23] Hybrid Gromov-Wasserstein Embedding for Capsule Learning
    Shamsolmoali, Pourya
    Zareapoor, Masoumeh
    Das, Swagatam
    Granger, Eric
    Garcia, Salvador
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, : 1 - 15
  • [24] Accelerate rotation invariant sliced Gromov-Wasserstein distance by an alternative optimization method
    Luo, Jinming
    Bian, Yuhao
    Gao, Xianjie
    Liu, Jian
    Liu, Xiuping
    INFORMATION SCIENCES, 2024, 677
  • [25] Gromov-Wasserstein Alignment of Word Embedding Spaces
    Alvarez-Melis, David
    Jaakkola, Tommi S.
    2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 1881 - 1890
  • [26] Gromov-Wasserstein distances between Gaussian distributions
    Delon, Julie
    Desolneux, Agnes
    Salmona, Antoine
    JOURNAL OF APPLIED PROBABILITY, 2022, 59 (04) : 1178 - 1198
  • [27] Entropic Gromov-Wasserstein between Gaussian Distributions
    Khang Le
    Dung Le
    Huy Nguyen
    Dat Do
    Tung Pham
    Nhat Ho
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [28] On the Existence of Monge Maps for the Gromov-Wasserstein Problem
    Dumont, Theo
    Lacombe, Theo
    Vialard, Francois-Xavier
    FOUNDATIONS OF COMPUTATIONAL MATHEMATICS, 2024, 25 (2) : 463 - 510
  • [29] Computing the Gromov-Wasserstein Distance between Two Surface Meshes Using Optimal Transport
    Koehl, Patrice
    Delarue, Marc
    Orland, Henri
    ALGORITHMS, 2023, 16 (03)
  • [30] Gromov-Wasserstein Distances and the Metric Approach to Object Matching
    Memoli, Facundo
    FOUNDATIONS OF COMPUTATIONAL MATHEMATICS, 2011, 11 (04) : 417 - 487