arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.06595cs.CGcs.LGmath.OC
收藏

图数据中Gromov-Wasserstein松弛的收敛单圈算法

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

Stanford University(斯坦福大学);HKUST (GZ)(香港科技大学(广州));CUHK(香港中文大学);SUFE(上海财经大学)

Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet

摘要:

在这项工作中,我们提出了Bregman交替投影梯度(BAPG)方法,一个单循环算法,提供了一个近似的解决方案的Gromov-Wasserstein(GW)距离。我们介绍了一种新的松弛技术,平衡精度和计算效率,虽然有一些妥协的耦合映射的可行性。我们的分析是基于GW问题满足Luo-Tseng误差界条件的观察,该误差界条件涉及基于最优性残差估计点到GW问题的临界点集的距离。这一观察使我们能够提供一个近似界的BAPG的不动点集和GW的临界点集之间的距离。此外,在一个温和的技术假设下,我们可以证明BAPG收敛到它的不动点集。BAPG的有效性已通过全面的数值实验在图对齐和分区任务,它优于现有的方法在解决方案的质量和挂钟时间方面进行了验证。

英文摘要:

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.

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。

↑