arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.06266math.OC
收藏

有监督 Gromov-Wasserstein 最优传输

Supervised Gromov-Wasserstein Optimal Transport

Zixuan Cang, Yaqi Wu, Yanxiang Zhao

AI总结:

本文提出有监督 Gromov-Wasserstein 最优传输,通过代价张量中的无穷模式施加距离保持等约束,并结合最小顶点覆盖与 Mirror-C 下降求解,在合成数据和单细胞 RNA 测序数据上验证了其控制距离保持和自动估计重叠部分的能力。

摘要:

我们引入了有监督 Gromov-Wasserstein(sGW)最优传输,这是 Gromov-Wasserstein 的一种扩展,通过在代价张量中纳入潜在的无穷模式来实现。sGW 通过将约束实现为无穷模式,使得能够施加由应用诱导的约束,例如保持成对距离。针对 sGW 问题提出了一种数值求解器,并在多种数值实验中证明了其有效性。sGW 中的高阶约束通过求解最小顶点覆盖问题被转化为对耦合矩阵的约束。转化后的问题通过 Mirror-C 下降迭代结合有监督最优传输求解器来求解。在数值实验中,我们首先通过将其应用于匹配合成数据集并研究模型参数的影响来验证所提出的框架。此外,我们成功地将 sGW 应用于真实的单细胞 RNA 测序数据。通过与其他 Gromov-Wasserstein 变体在真实数据上的比较,我们证明 sGW 提供了控制距离保持的新颖功能,从而能够自动估计数据集的重叠部分,这在数据驱动的应用中带来了更高的稳定性和灵活性。

英文摘要:

We introduce the supervised Gromov-Wasserstein (sGW) optimal transport, an extension of Gromov-Wasserstein by incorporating potential infinity patterns in the cost tensor. sGW enables the enforcement of application-induced constraints such as the preservation of pairwise distances by implementing the constraints as an infinity pattern. A numerical solver is proposed for the sGW problem and the effectiveness is demonstrated in various numerical experiments. The high-order constraints in sGW are transferred to constraints on the coupling matrix by solving a minimal vertex cover problem. The transformed problem is solved by the Mirror-C descent iteration coupled with the supervised optimal transport solver. In the numerical experiments, we first validate the proposed framework by applying it to matching synthetic datasets and investigating the impact of the model parameters. Additionally, we successfully apply sGW to real single-cell RNA sequencing data. Through comparisons with other Gromov-Wasserstein variants on real data, we demonstrate that sGW offers the novel utility of controlling distance preservation, leading to the automatic estimation of overlapping portions of datasets, which brings improved stability and flexibility in data-driven applications.

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。

↑