EUVIMEDEUVIMED entdecken
Crossref

Adaptive Riemannian Graph Neural Networks

Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (31) · 26606-26614

DOI: 10.1609/aaai.v40i31.39869 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xudong Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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's structural landscape. Our core innovation is an efficient parameterization of the node-wise metric tensor, specializing to a learnable diagonal form that captures directional geometric information while maintaining computational tractability. To ensure geometric regularity and stable training, we integrate a Ricci flow-inspired regularization that smooths the learned manifold. Theoretically, we establish the rigorous geometric evolution convergence guarantee for ARGNN and provide a continuous generalization that unifies prior fixed or mixed-curvature GNNs. Empirically, our method demonstrates superior performance on both homophilic and heterophilic benchmark datasets with the ability to capture diverse structures adaptively. Moreover, the learned geometries both offer interpretable insights into the underlying graph structure and empirically corroborate our theoretical analysis.

Zitieren

APA

Wang, X., Ding, C., Li, T., & Fan, J. (2026). Adaptive Riemannian Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 40(31), 26606-26614. https://doi.org/10.1609/aaai.v40i31.39869

Vancouver

Wang X, Ding C, Li T, Fan J. Adaptive Riemannian Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(31):26606-26614. doi:10.1609/aaai.v40i31.39869

BibTeX
@article{Wang2026,
  author = {Wang, Xudong and Ding, Chris and Li, Tongxin and Fan, Jicong},
  title = {Adaptive Riemannian Graph Neural Networks},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {31},
  pages = {26606--26614},
  doi = {10.1609/aaai.v40i31.39869}
}
Kostenlos starten →