Proceedings

DHTAGK: Deep Hierarchical Transitive-Aligned Graph Kernels for Graph Classification

Xinya Qin, Lu Bai, Lixin Cui, Ming Li, Ziyu Lyu, Hangyuan Du, Edwin Hancock

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 3254-3262.

https://doi.org/10.24963/ijcai.2025/362

Keywords

  • Data Mining: DM: Mining graphs
  • Machine Learning: ML: Kernel methods

Abstract

In this paper, we propose a family of novel Deep Hierarchical Transitive-Aligned Graph Kernels (DHTAGK) for graph classification. To this end, we commence by developing a new Hierarchical Aligned Graph Auto-Encoder (HA-GAE) to construct transitive-aligned embedding graphs that encapsulate the structural correspondence information between graphs. The DHTAGK kernels then measure either the Jensen-Shannon Divergence between the adjacency matrices or the Gaussian kernel between the node feature matrices of the embedding graphs. Unlike the classical R-convolution kernels and node-based alignment kernels, the DHTAGK kernels can capture the transitive structural correspondence information and thus ensure the positive definiteness. Furthermore, the HA-GAE enables the DHTAGK kernels to simultaneously reflect both local and global graph structures and identify common structural patterns. Experimental results show that the DHTAGK kernels outperform state-of-the-art graph kernels and deep learning methods on benchmark datasets.

Xinya Qin, Lu Bai, Lixin Cui, Ming Li, Ziyu Lyu, Hangyuan Du, and Edwin Hancock. 2025. DHTAGK: Deep Hierarchical Transitive-Aligned Graph Kernels for Graph Classification. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 3254–3262. https://doi.org/10.24963/ijcai.2025/362
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards