Quantized Gromov-Wasserstein

04/05/2021
by   Samir Chowdhury, et al.
5

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 sketching 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.

READ FULL TEXT
research
11/09/2020

A contribution to Optimal Transport on incomparable spaces

Optimal Transport is a theory that allows to define geometrical notions ...
research
11/18/2022

Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections

It has been shown beneficial for many types of data which present an und...
research
05/23/2018

Optimal Transport for structured data

Optimal transport has recently gained a lot of interest in the machine l...
research
12/11/2020

Randomised Wasserstein Barycenter Computation: Resampling with Statistical Guarantees

We propose a hybrid resampling method to approximate finitely supported ...
research
07/18/2023

Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spaces

This paper presents a framework for computing the Gromov-Wasserstein pro...
research
11/16/2022

Unbalanced Optimal Transport, from Theory to Numerics

Optimal Transport (OT) has recently emerged as a central tool in data sc...
research
08/07/2022

Kernel Biclustering algorithm in Hilbert Spaces

Biclustering algorithms partition data and covariates simultaneously, pr...

Please sign up or login with your details

Forgot password? Click here to reset