A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning
A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning
复制标题
DOI：
10.1145/3511808.3557222
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Li Sun;Junda Ye;Hao Peng;Philip S. Yu
中科院分区：
文献类型：
--
作者：
Li Sun;Junda Ye;Hao Peng;Philip S. Yu
时态图的表示学习由于其在现实世界中的广泛应用中的重要性而引起了广泛的研究关注。虽然一些研究成功地获得了时间依赖的表征，但它仍然面临着重大的挑战。一方面，现有的嵌入方法大多将嵌入空间限制在一定的曲率范围内。然而，其基本几何事实上是在正曲率超球面、零曲率欧氏空间和负曲率双曲空间之间随时间演化的。另一方面，这些方法通常需要大量的标签来学习时间表示，从而显着限制了它们在真实的应用中的无标签图的广泛使用。为了弥合这一差距，我们首次尝试研究一般黎曼空间中的自监督时间图表示学习问题，支持时变曲率在超球面，欧几里得和双曲空间之间转移。本文提出了一种新的自监督黎曼图神经网络（Self-Supervised Riemann Graph Neural Network，Self-GNNN）。具体来说，我们设计了一个曲率变化的黎曼GNN与理论接地时间编码，并制定了一个功能曲率随时间的推移，以模拟正，零和负曲率空间之间的演变转移。为了实现自监督学习，我们提出了一种新的重加权自对比方法，在没有增强的情况下探索黎曼空间本身，并提出了一种基于Ricci曲率的基于边缘的自监督曲率学习。大量的实验表明了SelfRGNN的优越性，而且，案例研究显示了现实中时间图的时变曲率。
Representation learning on temporal graphs has drawn considerable research attention owing to its fundamental importance in a wide spectrum of real-world applications. Though a number of studies succeed in obtaining time-dependent representations, it still faces significant challenges. On the one hand, most of the existing methods restrict the embedding space with a certain curvature. However, the underlying geometry in fact shifts among the positive curvature hyperspherical, zero curvature Euclidean and negative curvature hyperbolic spaces in the evolvement over time. On the other hand, these methods usually require abundant labels to learn temporal representations, and thereby notably limit their wide use in the unlabeled graphs of the real applications. To bridge this gap, we make the first attempt to study the problem of self-supervised temporal graph representation learning in the general Riemannian space, supporting the time-varying curvature to shift among hyperspherical, Euclidean and hyperbolic spaces. In this paper, we present a novel self-supervised Riemannian graph neural network (SelfℛGNN). Specifically, we design a curvature-varying Riemannian GNN with a theoretically grounded time encoding, and formulate a functional curvature over time to model the evolvement shifting among the positive, zero and negative curvature spaces. To enable the self-supervised learning, we propose a novel reweighting self-contrastive approach, exploring the Riemannian space itself without augmentation, and propose an edge-based self-supervised curvature learning with the Ricci curvature. Extensive experiments show the superiority of SelfRGNN, and moreover, the case study shows the time-varying curvature of temporal graph in reality.