Graph kernel neural networks: a preliminary review

Graphical abstract

References

[1] Shervashidze N, Schweitzer P, Van Leeuwen E J, Mehlhorn K, Borgwardt K M . Weisfeiler-lehman graph kernels. The Journal of Machine Learning Research, 2011, 12: 2539–2561

[2] Xu K, Hu W, Leskovec J, Jegelka S. How powerful are graph neural networks?. In: Proceedings of International Conference on Learning Representations. 2019

[3] Qian F, Bai L, Cui L, Li M, Du H, Wang Y, Hancock E. Exploring the over-smoothing problem of graph neural networks for graph classification: an entropy-based viewpoint. In: Proceedings of the 34th International Joint Conference on Artificial Intelligence. 2025, 360

[4] Nikolentzos G, Vazirgiannis M. Random walk graph neural networks. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 1360

[5] Feng A, You C, Wang S, Tassiulas L. KerGNNs: interpretable graph neural networks with graph kernels. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence. 2022, 6614−6622

[6] Cosmo L, Minello G, Bicciato A, Bronstein M M, Rodolà E, Rossi L, Torsello A . Graph kernel neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36( 4): 6257–6270

[7] Chen D, Jacob L, Mairal J. Convolutional kernel networks for graph-structured data. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 147

[8] Yu J, Wu Z, Cai J, Jia A L, Fan J. Kernel readout for graph neural networks. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence. 2024, 277

[9] Xu L, Peng J, Jiang X, Chen E, Luo B . Graph neural network based on graph kernel: a survey. Pattern Recognition, 2025, 161: 111307

[10] Haussler D. Convolution kernels on discrete structures. UCSC-CRL-99-10. Santa Cruz: Department of Computer Science, University of California, 1999

[11] Bai L, Cui L, Jiao Y, Rossi L, Hancock E R . Learning backtrackless aligned-spatial graph convolutional networks for graph classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44( 2): 783–798

[12] Cui L, Bai L, Rossi L, Wang Y, Jiao Y, Hancock E R. A deep hybrid graph kernel through deep learning networks. In: Proceedings of the 24th International Conference on Pattern Recognition. 2018, 1030−1035

[13] Qian F, Bai L, Cui L, Li M, Lyu Z, Du H, Hancock E R. DHAKR: learning deep hierarchical attention-based kernelized representations for graph classification. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence. 2025, 19995−20003

[14] Du S S, Hou K, Póczos R, Salakhutdinov R, Wang R, Xu K. Graph neural tangent kernel: fusing graph neural networks with graph kernels. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 514

[15] Bai L, Cui L, Li M, Ren P, Wang Y, Zhang L, Yu P S, Hancock E R . AEGK: aligned entropic graph kernels through continuous-time quantum walks. IEEE Transactions on Knowledge and Data Engineering, 2025, 37( 3): 1064–1078

[16] Bai L, Jiao Y, Cui L, Rossi L, Wang Y, Yu P S, Hancock E R . Learning graph convolutional networks based on quantum vertex information propagation. IEEE Transactions on Knowledge and Data Engineering, 2023, 35( 2): 1747–1760

[17] Cui L, Li M, Bai L, Wang Y, Li J, Wang Y, Li Z, Chen Y, Hancock E R . QBER: quantum-based entropic representations for un-attributed graphs. Pattern Recognition, 2024, 145: 109877

RIGHTS & PERMISSIONS

Higher Education Press