Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower Bound

05/12/2022
by   Hongwei Jin, et al.
0

Comparing structured data from possibly different metric-measure spaces is a fundamental task in machine learning, with applications in, e.g., graph classification. The Gromov-Wasserstein (GW) discrepancy formulates a coupling between the structured data based on optimal transportation, tackling the incomparability between different structures by aligning the intra-relational geometries. Although efficient local solvers such as conditional gradient and Sinkhorn are available, the inherent non-convexity still prevents a tractable evaluation, and the existing lower bounds are not tight enough for practical use. To address this issue, we take inspiration from the connection with the quadratic assignment problem, and propose the orthogonal Gromov-Wasserstein (OGW) discrepancy as a surrogate of GW. It admits an efficient and closed-form lower bound with the complexity of 𝒪(n^3), and directly extends to the fused Gromov-Wasserstein (FGW) distance, incorporating node features into the coupling. Extensive experiments on both the synthetic and real-world datasets show the tightness of our lower bounds, and both OGW and its lower bounds efficiently deliver accurate predictions and satisfactory barycenters for graph sets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/14/2023

On the Gap between Hereditary Discrepancy and the Determinant Lower Bound

The determinant lower bound of Lovasz, Spencer, and Vesztergombi [Europe...
research
10/04/2019

Fused Gromov-Wasserstein Alignment for Hawkes Processes

We propose a novel fused Gromov-Wasserstein alignment method to jointly ...
research
03/19/2019

A New Lower Bound for Semigroup Orthogonal Range Searching

We report the first improvement in the space-time trade-off of lower bou...
research
02/16/2021

Unifying Lower Bounds on Prediction Dimension of Consistent Convex Surrogates

Given a prediction task, understanding when one can and cannot design a ...
research
05/26/2022

Efficient Approximation of Gromov-Wasserstein Distance using Importance Sparsification

As a valid metric of metric-measure spaces, Gromov-Wasserstein (GW) dist...
research
03/15/2023

Combinatorial Designs Meet Hypercliques: Higher Lower Bounds for Klee's Measure Problem and Related Problems in Dimensions d≥ 4

Klee's measure problem (computing the volume of the union of n axis-para...
research
02/03/2020

Conditional Indexing Lower Bounds Through Self-Reducibility

We provide a general technique to turn a conditional lower bound result ...

Please sign up or login with your details

Forgot password? Click here to reset