CSGO:用于大图匹配的约束软分配梯度优化
CSGO: Constrained-Softassign Gradient Optimization For Large Graph Matching
AI总结:
本文提出 CSGO 框架,通过自适应步长保证约束梯度法收敛,并以可扩展 softassign 提升大图匹配的速度、鲁棒性与抗溢出能力,实验性能优于现有方法,属性图匹配速度提升超10倍。
摘要:
图匹配旨在寻找两个图之间的对应关系。本文将若干著名的图匹配算法整合到一个框架中:约束梯度法。这些算法之间的主要区别在于调整步长参数和约束算子。通过利用这些洞见,我们提出了一种自适应步长参数,以保证底层算法的收敛性,同时提升其效率和鲁棒性。对于约束算子,我们引入了一种适用于大图匹配问题的可扩展 softassign(软分配)。与原始 softassign 相比,我们的方法速度更快、鲁棒性更强,并降低了溢出风险。这一先进的约束算子促成了用于大图匹配的 CSGO,其在实验中优于最先进的方法。值得注意的是,在属性图匹配任务中,与当前的约束梯度算法相比,CSGO 实现了超过 10 倍的速度提升。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。