论文标题
CSGO：用于大图匹配的约束软座梯度优化
CSGO: Constrained-Softassign Gradient Optimization For Large Graph Matching
论文作者
论文摘要
图匹配旨在查找两个图之间的对应关系。本文将几种众所周知的图形匹配算法集成到一个框架中：约束梯度方法。这些算法之间的主要区别在于调整步长参数和约束操作员。通过利用这些见解，我们提出了一个自适应步长参数，以确保潜在算法的收敛性，同时提高其效率和鲁棒性。对于约束操作员，我们为大图匹配问题引入了可伸缩软设备。与原始软件相比，我们的方法提供了提高速度，提高鲁棒性和溢出风险的降低。高级约束操作员为大图匹配提供了CSGO，在实验中的最新方法优于最先进的方法。值得注意的是，与当前受约束梯度算法相比，CSGO在归因的图形匹配任务中的速度超过10倍。
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.
