基于单纯复形上花瓣 Laplacian 的高阶图卷积网络
Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes
AI总结:
针对图神经网络难以建模和量化高阶交互的问题,本文提出基于 FP Laplacian 的 HiGCN,利用可学习滤波器跨拓扑尺度提取特征并度量交互强度,在多项图任务上达到最先进性能。
摘要:
尽管普通图神经网络(GNN)近期在多种任务上取得了成功,但其建立在成对网络之上的基础固有地限制了其识别复杂系统中潜在高阶交互的能力。为弥合这一能力差距,我们提出了一种利用单纯复形(SC)丰富数学理论的新方法;SC 是用于建模高阶交互的强大工具。当前基于 SC 的 GNN 受制于高复杂性和刚性,而且量化高阶交互强度仍然具有挑战性。我们创新性地提出了一种高阶 Flower-Petals(FP,花瓣)模型,将 FP Laplacian 纳入 SC。此外,我们介绍了一种基于 FP Laplacian 的高阶图卷积网络(HiGCN),它能够识别不同拓扑尺度上的内在特征。通过采用可学习图滤波器——每个 FP Laplacian 域内的一组参数——我们可以识别多样的模式,其中滤波器权重充当高阶交互强度的可量化度量。文中严格证明了 HiGCN 先进表达能力的理论基础。此外,我们的实证研究表明,所提出模型在一系列图任务上达到了最先进性能,并为探索图中的高阶交互提供了可扩展且灵活的解决方案。代码和数据集可在 https://github.com/Yiminghh/HiGCN 获取。
英文摘要:
Despite the recent successes of vanilla Graph Neural Networks (GNNs) on various tasks, their foundation on pairwise networks inherently limits their capacity to discern latent higher-order interactions in complex systems. To bridge this capability gap, we propose a novel approach exploiting the rich mathematical theory of simplicial complexes (SCs) - a robust tool for modeling higher-order interactions. Current SC-based GNNs are burdened by high complexity and rigidity, and quantifying higher-order interaction strengths remains challenging. Innovatively, we present a higher-order Flower-Petals (FP) model, incorporating FP Laplacians into SCs. Further, we introduce a Higher-order Graph Convolutional Network (HiGCN) grounded in FP Laplacians, capable of discerning intrinsic features across varying topological scales. By employing learnable graph filters, a parameter group within each FP Laplacian domain, we can identify diverse patterns where the filters' weights serve as a quantifiable measure of higher-order interaction strengths. The theoretical underpinnings of HiGCN's advanced expressiveness are rigorously demonstrated. Additionally, our empirical investigations reveal that the proposed model accomplishes state-of-the-art performance on a range of graph tasks and provides a scalable and flexible solution to explore higher-order interactions in graphs. Codes and datasets are available at https://github.com/Yiminghh/HiGCN.
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。