Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310561518> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4310561518 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." @default.
- W4310561518 created "2022-12-12" @default.
- W4310561518 creator A5000597313 @default.
- W4310561518 creator A5036357902 @default.
- W4310561518 creator A5051671090 @default.
- W4310561518 creator A5069093595 @default.
- W4310561518 creator A5078537850 @default.
- W4310561518 date "2022-11-30" @default.
- W4310561518 modified "2023-09-26" @default.
- W4310561518 title "Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces" @default.
- W4310561518 doi "https://doi.org/10.48550/arxiv.2211.17068" @default.
- W4310561518 hasPublicationYear "2022" @default.
- W4310561518 type Work @default.
- W4310561518 citedByCount "0" @default.
- W4310561518 crossrefType "posted-content" @default.
- W4310561518 hasAuthorship W4310561518A5000597313 @default.
- W4310561518 hasAuthorship W4310561518A5036357902 @default.
- W4310561518 hasAuthorship W4310561518A5051671090 @default.
- W4310561518 hasAuthorship W4310561518A5069093595 @default.
- W4310561518 hasAuthorship W4310561518A5078537850 @default.
- W4310561518 hasBestOaLocation W43105615181 @default.
- W4310561518 hasConcept C11413529 @default.
- W4310561518 hasConcept C119857082 @default.
- W4310561518 hasConcept C132525143 @default.
- W4310561518 hasConcept C154945302 @default.
- W4310561518 hasConcept C195065555 @default.
- W4310561518 hasConcept C2524010 @default.
- W4310561518 hasConcept C33923547 @default.
- W4310561518 hasConcept C41008148 @default.
- W4310561518 hasConcept C80444323 @default.
- W4310561518 hasConceptScore W4310561518C11413529 @default.
- W4310561518 hasConceptScore W4310561518C119857082 @default.
- W4310561518 hasConceptScore W4310561518C132525143 @default.
- W4310561518 hasConceptScore W4310561518C154945302 @default.
- W4310561518 hasConceptScore W4310561518C195065555 @default.
- W4310561518 hasConceptScore W4310561518C2524010 @default.
- W4310561518 hasConceptScore W4310561518C33923547 @default.
- W4310561518 hasConceptScore W4310561518C41008148 @default.
- W4310561518 hasConceptScore W4310561518C80444323 @default.
- W4310561518 hasLocation W43105615181 @default.
- W4310561518 hasOpenAccess W4310561518 @default.
- W4310561518 hasPrimaryLocation W43105615181 @default.
- W4310561518 hasRelatedWork W2961085424 @default.
- W4310561518 hasRelatedWork W3046775127 @default.
- W4310561518 hasRelatedWork W3170094116 @default.
- W4310561518 hasRelatedWork W4205958290 @default.
- W4310561518 hasRelatedWork W4225307033 @default.
- W4310561518 hasRelatedWork W4285260836 @default.
- W4310561518 hasRelatedWork W4286629047 @default.
- W4310561518 hasRelatedWork W4306321456 @default.
- W4310561518 hasRelatedWork W4306674287 @default.
- W4310561518 hasRelatedWork W4224009465 @default.
- W4310561518 isParatext "false" @default.
- W4310561518 isRetracted "false" @default.
- W4310561518 workType "article" @default.