Dynamical softassign and adaptive parameter tuning for graph matching

08/17/2022
by   Binrui Shen, et al.
0

This paper studies a framework, projected fixed-point method, for graph matching. The framework contains a class of popular graph matching algorithms, including graduated assignment (GA), integer projected fixed-point method (IPFP) and doubly stochastic projected fixed-point method (DSPFP). We propose an adaptive strategy to tune the step size parameter in this framework. Such a strategy improves these algorithms in efficiency and accuracy. Further, it guarantees the convergence of the underlying algorithms. Some preliminary analysis based on distance geometry seems to support that the optimal step size parameter has a high probability of 1 when graphs are fully connected. Secondly, it is observed that a popular projection method, softassign, is sensitive to graphs' cardinality(size). We proposed a dynamical softassign algorithm that is robust to graphs' cardinality. Combining the adaptive step size and the dynamical softassign, we propose a novel graph matching algorithm: the adaptive projected fixed-point method with dynamical softassign. Various experiments demonstrate that the proposed algorithm is significantly faster than several other state-of-art algorithms with no loss of accuracy.

READ FULL TEXT

page 12

page 14

research
07/03/2012

A Fast Projected Fixed-Point Algorithm for Large Graph Matching

We propose a fast approximate algorithm for large graph matching. A new ...
research
09/18/2019

Fixed Point Analysis of Douglas-Rachford Splitting for Ptychography and Phase Retrieval

Douglas-Rachford Splitting (DRS) methods based on the proximal point alg...
research
04/03/2018

A Constant Step Stochastic Douglas-Rachford Algorithm with Application to Non Separable Regularizations

The Douglas Rachford algorithm is an algorithm that converges to a minim...
research
05/22/2018

Step Size Matters in Deep Learning

Training a neural network with the gradient descent algorithm gives rise...
research
02/19/2021

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods

We present an adaptive stochastic variance reduced method with an implic...
research
04/08/2022

Seeded graph matching for the correlated Wigner model via the projected power method

In the graph matching problem we observe two graphs G,H and the goal is ...
research
03/12/2023

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

In this work, we present the Bregman Alternating Projected Gradient (BAP...

Please sign up or login with your details

Forgot password? Click here to reset