arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.08149cs.LGcs.AI
收藏

通过电阻曲率流实现动态图结构学习

Dynamic Graph Structure Learning via Resistance Curvature Flow

School of Artificial Intelligence, South China Normal University(人工智能学院,华南师范大学);School of Computer Science, South China Normal University(计算机科学学院,华南师范大学);State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(数学科学国家重点实验室,数学与系统科学研究院,中国科学院)

Chaoqun Fei, Huanjiang Liu, Tinglve Zhou, Yangyang Li, Tianyong Hao

AI总结:

本文提出电阻曲率流方法,通过有效电阻概念实现高效图结构学习,显著提升表示质量和下游任务性能。

摘要:

几何表示学习(GRL)旨在通过离散图结构近似高维数据的非欧几里得拓扑,基于流形假设。然而,基于欧几里得距离的传统静态图构建方法往往无法捕捉数据流形的内在曲率特征。尽管Ollivier-Ricci曲率流(OCF)已被证明是动态拓扑优化的强大工具,但其核心依赖于最优传输(Wasserstein距离)导致计算复杂度过高,严重限制了其在大规模数据集和深度学习框架中的应用。为突破这一瓶颈,本文提出了一种新的几何演化框架:电阻曲率流(RCF)。利用电路物理学中的有效电阻概念,RCF将昂贵的曲率优化转化为高效的矩阵运算。该方法在保持与OCF相当的几何优化能力的同时,实现了超过100倍的计算加速。我们深入探讨了RCF的理论基础和动态原理,阐明了它如何通过曲率梯度引导边权的重新分布以消除拓扑噪声并强化局部聚类结构。此外,我们提供了RCF在流形增强和噪声抑制以及与深度学习模型兼容性的机理解释。我们基于此框架设计了一个图优化算法DGSL-RCF。在深度度量学习、流形学习和图结构学习中的实验结果表明,DGSL-RCF显著提高了表示质量和下游任务性能。

英文摘要:

Geometric Representation Learning (GRL) aims to approximate the non-Euclidean topology of high-dimensional data through discrete graph structures, grounded in the manifold hypothesis. However, traditional static graph construction methods based on Euclidean distance often fail to capture the intrinsic curvature characteristics of the data manifold. Although Ollivier-Ricci Curvature Flow (OCF) has proven to be a powerful tool for dynamic topological optimization, its core reliance on Optimal Transport (Wasserstein distance) leads to prohibitive computational complexity, severely limiting its application in large-scale datasets and deep learning frameworks. To break this bottleneck, this paper proposes a novel geometric evolution framework: Resistance Curvature Flow (RCF). Leveraging the concept of effective resistance from circuit physics, RCF transforms expensive curvature optimization into efficient matrix operations. This approach achieves over 100x computational acceleration while maintaining geometric optimization capabilities comparable to OCF. We provide an in-depth exploration of the theoretical foundations and dynamical principles of RCF, elucidating how it guides the redistribution of edge weights via curvature gradients to eliminate topological noise and strengthen local cluster structures. Furthermore, we provide a mechanistic explanation of RCF's role in manifold enhancement and noise suppression, as well as its compatibility with deep learning models. We design a graph optimization algorithm, DGSL-RCF, based on this framework. Experimental results across deep metric learning, manifold learning, and graph structure learning demonstrate that DGSL-RCF significantly improves representation quality and downstream task performance.

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。

↑