Saved in:
Bibliographic Details
Main Authors: Shen, Binrui, Niu, Qiang, Zhu, Shengxin
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2208.08233
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913604712792064
author Shen, Binrui
Niu, Qiang
Zhu, Shengxin
author_facet Shen, Binrui
Niu, Qiang
Zhu, Shengxin
contents Graph matching aims to find correspondences between two graphs. This paper integrates several well-known graph matching algorithms into a framework: the constrained gradient method. The primary difference among these algorithms lies in tuning a step size parameter and constraining operators. By leveraging these insights, we propose an adaptive step size parameter to guarantee the underlying algorithms' convergence, simultaneously enhancing their efficiency and robustness. For the constraining operator, we introduce a scalable softassign for large graph matching problems. Compared to the original softassign, our approach offers increased speed, improved robustness, and reduced risk of overflow. The advanced constraining operator enables a CSGO for large graph matching, which outperforms state-of-the-art methods in experiments. Notably, in attributed graph matching tasks, CSGO achieves an over 10X increase in speed compared to current constrained gradient algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2208_08233
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle CSGO: Constrained-Softassign Gradient Optimization For Large Graph Matching
Shen, Binrui
Niu, Qiang
Zhu, Shengxin
Combinatorics
Machine Learning
Graph matching aims to find correspondences between two graphs. This paper integrates several well-known graph matching algorithms into a framework: the constrained gradient method. The primary difference among these algorithms lies in tuning a step size parameter and constraining operators. By leveraging these insights, we propose an adaptive step size parameter to guarantee the underlying algorithms' convergence, simultaneously enhancing their efficiency and robustness. For the constraining operator, we introduce a scalable softassign for large graph matching problems. Compared to the original softassign, our approach offers increased speed, improved robustness, and reduced risk of overflow. The advanced constraining operator enables a CSGO for large graph matching, which outperforms state-of-the-art methods in experiments. Notably, in attributed graph matching tasks, CSGO achieves an over 10X increase in speed compared to current constrained gradient algorithms.
title CSGO: Constrained-Softassign Gradient Optimization For Large Graph Matching
topic Combinatorics
Machine Learning
url https://arxiv.org/abs/2208.08233