Adaptive Riemannian Graph Neural Networks

Xudong Wang; Chris Ding; Tongxin Li; Jicong Fan

AAAI 2026technical0 citations

Adaptive Riemannian Graph Neural Networks

Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan

Abstract

Graph data often exhibits complex geometric heterogeneity, where structures with varying local curvature, such as tree-like hierarchies and dense communities, coexist within a single network. Existing geometric GNNs, which embed graphs into single fixed-curvature manifolds or discrete product spaces, struggle to capture this diversity. We introduce Adaptive Riemannian Graph Neural Networks (ARGNN), a novel framework that learns a continuous and anisotropic Riemannian metric tensor field over the graph. It allows each node to determine its optimal local geometry, enabling the model to fluidly adapt to the graph

BibTeX

@inproceedings{aaai2026_adaptiveriemanni,
  title = {Adaptive Riemannian Graph Neural Networks},
  author = {Xudong Wang and Chris Ding and Tongxin Li and Jicong Fan},
  booktitle = {AAAI 2026},
  year = {2026}
}