DeepAI AI Chat
Log In Sign Up

A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data

by   Jiajin Li, et al.
The Chinese University of Hong Kong
Stanford University
The Hong Kong University of Science and Technology

In this work, we present the Bregman Alternating Projected Gradient (BAPG) method, a single-loop algorithm that offers an approximate solution to the Gromov-Wasserstein (GW) distance. We introduce a novel relaxation technique that balances accuracy and computational efficiency, albeit with some compromises in the feasibility of the coupling map. Our analysis is based on the observation that the GW problem satisfies the Luo-Tseng error bound condition, which relates to estimating the distance of a point to the critical point set of the GW problem based on the optimality residual. This observation allows us to provide an approximation bound for the distance between the fixed-point set of BAPG and the critical point set of GW. Moreover, under a mild technical assumption, we can show that BAPG converges to its fixed point set. The effectiveness of BAPG has been validated through comprehensive numerical experiments in graph alignment and partition tasks, where it outperforms existing methods in terms of both solution quality and wall-clock time.


Fast and Provably Convergent Algorithms for Gromov-Wasserstein in Graph Learning

In this paper, we study the design and analysis of a class of efficient ...

Optimization over Sparse Symmetric Sets via a Nonmonotone Projected Gradient Method

We consider the problem of minimizing a Lipschitz differentiable functio...

Data-driven Reconstruction of Nonlinear Dynamics from Sparse Observation

We present a data-driven model to reconstruct nonlinear dynamics from a ...

A Closed-Form Bound on the Asymptotic Linear Convergence of Iterative Methods via Fixed Point Analysis

In many iterative optimization methods, fixed-point theory enables the a...

Clustering with Iterated Linear Optimization

We introduce a novel method for clustering using a semidefinite programm...

Dynamical softassign and adaptive parameter tuning for graph matching

This paper studies a framework, projected fixed-point method, for graph ...

Application of accelerated fixed-point algorithms to hydrodynamic well-fracture coupling

The coupled simulations of dynamic interactions between the well, hydrau...