AAAI · 2026

Adaptive Riemannian Graph Neural Networks

Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan

Proceedings of the AAAI Conference on Artificial Intelligence

Read paper PDF Repository BibTeX
Wisconsin network topology colored by class beside a three dimensional embedding with a curvature shaded surface.

AAAI · 2026

One graph, many local geometries

The Wisconsin network has heterogeneous local structure. Its topology and feature embedding motivate learning a separate Riemannian metric at each node rather than imposing one geometry on the entire graph.

Adaptive Riemannian Graph Neural Networks Figure 1 from the paper

How can a graph model adapt to different local geometries?

ARGNN learns a node specific Riemannian metric instead of imposing one fixed curvature on an entire graph. A diagonal metric parameterization and geometric regularization support efficient training, with convergence analysis and experiments on homophilic and heterophilic graphs.

Research themes

Cite this paper

Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan. Adaptive Riemannian Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 2026. https://doi.org/10.1609/aaai.v40i31.39869

BibTeX
@inproceedings{tongxin-argnn,
  title = {{Adaptive Riemannian Graph Neural Networks}},
  author = {Xudong Wang and Chris Ding and Tongxin Li and Jicong Fan},
  year = {2026},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  url = {https://doi.org/10.1609/aaai.v40i31.39869},
  doi = {10.1609/aaai.v40i31.39869}
}
2026CSEE JPES

Quantum Learning and Estimation for Coordinated Operation between Distribution Networks and Energy Communities

Yingrui Zhuang, Lin Cheng, Yuji Cao, Tongxin Li, Ning Qi, Yan Xu, Yue Chen

A hybrid quantum learning model estimates energy community responses to prices, while quantum amplitude estimation supports uncertainty calculations. Numerical studies assess accuracy and resource requirements. Reported timing advantages assume ideal quantum devices rather than deployed hardware.

Energy Information
Paper PDF