Gromov-Wasserstein Factorization Models for Graph Clustering

  title={Gromov-Wasserstein Factorization Models for Graph Clustering},
  author={H. Xu},
  • H. Xu
  • Published in AAAI 2020
  • Computer Science, Mathematics
  • We propose a new nonlinear factorization model for graphs that are with topological structures, and optionally, node attributes. This model is based on a pseudometric called Gromov-Wasserstein (GW) discrepancy, which compares graphs in a relational way. It estimates observed graphs as GW barycenters constructed by a set of atoms with different weights. By minimizing the GW discrepancy between each observed graph and its GW barycenter-based estimation, we learn the atoms and their weights… CONTINUE READING
    7 Citations
    Learning Graphons via Structured Gromov-Wasserstein Barycenters
    • PDF
    Online Graph Dictionary Learning
    • Highly Influenced
    • PDF
    Optimal Transport Graph Neural Networks
    • 2
    • PDF
    SWIFT: Scalable Wasserstein Factorization for Sparse Nonnegative Tensors
    • PDF
    Learning Autoencoders with Relational Regularization
    • 6
    • PDF
    Relational Thematic Clustering with Mutually Preferred Neighbors
    • PDF
    Hierarchical Optimal Transport for Robust Multi-View Learning
    • 1
    • PDF


    Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
    • 34
    • PDF
    Sliced Gromov-Wasserstein
    • 27
    • Highly Influential
    • PDF
    Gromov-Wasserstein Averaging of Kernel and Distance Matrices
    • 104
    • PDF
    Graph Kernels
    • 810
    • PDF
    Fast Discrete Distribution Clustering Using Wasserstein Barycenter With Sparse Support
    • 64
    • PDF
    Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning
    • 66
    • PDF
    Fast Dictionary Learning with a Smoothed Wasserstein Loss
    • 91
    • PDF
    Visualizing Data using t-SNE
    • 15,761
    • PDF