Status and perspectives of dynamic graph neural ordinary differential equations

Graphical abstract

References

[1] Zheng Y, Yi L, Wei Z . A survey of dynamic graph neural networks. Frontiers of Computer Science, 2025, 19( 6): 196323

[2] Jiao P F, Chen S X, Guo X, He D X, Liu D . Survey on graph neural ordinary differential equations. Journal of Computer Research and Development, 2024, 61( 8): 2045–2066

[3] Chen R T Q, Rubanova Y, Bettencourt J, Duvenaud D. Neural ordinary differential equations. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 6572−6583

[4] Butcher J C. Numerical Methods for Ordinary Differential Equations. 3rd ed. Hoboken: John Wiley & Sons, 2016

[5] Liu Z, Wang X, Wang B, Huang Z, Yang C, Jin W. Graph odes and beyond: A comprehensive survey on integrating differential equations with graph neural networks. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2025, 6118−6128

[6] Utkarsh U, Churavy V, Ma Y, Besard T, Srisuma P, Gymnich T, Gerlach A R, Edelman A, Barbastathis G, Braatz R D, Rackauckas C . Automated translation and accelerated solving of differential equations on multiple GPU platforms. Computer Methods in Applied Mechanics and Engineering, 2024, 419: 116591

[7] Gattiglio G, Grigoryeva L, Tamborrino M. RandNet-parareal: a time-parallel PDE solver using random neural networks. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 3011

[8] Chakaravarthy V T, Pandian S S, Raje S, Sabharwal Y, Suzumura T, Ubaru S. Efficient scaling of dynamic graph neural networks. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 2021, 77

RIGHTS & PERMISSIONS

Higher Education Press