Skip to main navigation Skip to search Skip to main content

Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces

  • Li Sun
  • , Junda Ye
  • , Hao Peng
  • , Feiyang Wang
  • , Philip S. Yu
  • North China Electric Power University
  • Beijing University of Posts and Telecommunications
  • University of Illinois at Chicago

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Continual graph learning routinely finds its role in a variety of real-world applications where the graph data with different tasks come sequentially. Despite the success of prior works, it still faces great challenges. On the one hand, existing methods work with the zero-curvature Euclidean space, and largely ignore the fact that curvature varies over the coming graph sequence. On the other hand, continual learners in the literature rely on abundant labels, but labeling graph in practice is particularly hard especially for the continuously emerging graphs on-the-fly. To address the aforementioned challenges, we propose to explore a challenging yet practical problem, the self-supervised continual graph learning in adaptive Riemannian spaces. In this paper, we propose a novel self-supervised Riemannian Graph Continual Learner (RieGrace). In RieGrace, we first design an Adaptive Riemannian GCN (AdaRGCN), a unified GCN coupled with a neural curvature adapter, so that Riemannian space is shaped by the learnt curvature adaptive to each graph. Then, we present a Label-free Lorentz Distillation approach, in which we create teacher-student AdaRGCN for the graph sequence. The student successively performs intra-distillation from itself and inter-distillation from the teacher so as to consolidate knowledge without catastrophic forgetting. In particular, we propose a theoretically grounded Generalized Lorentz Projection for the contrastive distillation in Riemannian space. Extensive experiments on the benchmark datasets show the superiority of RieGrace, and additionally, we investigate on how curvature changes over the graph sequence.

Original languageEnglish
Title of host publicationAAAI-23 Technical Tracks 4
EditorsBrian Williams, Yiling Chen, Jennifer Neville
PublisherAAAI press
Pages4633-4642
Number of pages10
ISBN (Electronic)9781577358800
DOIs
StatePublished - 27 Jun 2023
Event37th AAAI Conference on Artificial Intelligence, AAAI 2023 - Washington, United States
Duration: 7 Feb 202314 Feb 2023

Publication series

NameProceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
Volume37

Conference

Conference37th AAAI Conference on Artificial Intelligence, AAAI 2023
Country/TerritoryUnited States
CityWashington
Period7/02/2314/02/23

Fingerprint

Dive into the research topics of 'Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces'. Together they form a unique fingerprint.

Cite this