A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning

TL;DR

This paper introduces SelfRGNN, a self-supervised Riemannian GNN that models the evolving geometry of temporal graphs with time-varying curvature, enabling better representation learning without labels.

Contribution

It pioneers self-supervised temporal graph learning in a Riemannian space with dynamic curvature, supporting shifts among hyperspherical, Euclidean, and hyperbolic geometries.

Findings

SelfRGNN outperforms existing methods in experiments.

The model effectively captures time-varying curvature in real-world graphs.

Self-supervised approach reduces reliance on labeled data.

Abstract

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.