---
title: "DHTAGK: Deep Hierarchical Transitive-Aligned Graph Kernels for Graph Classification"
authors:
  - "Xinya Qin"
  - "Lu Bai"
  - "Lixin Cui"
  - "Ming Li"
  - "Ziyu Lyu"
  - "Hangyuan Du"
  - "Edwin Hancock"
doi: "10.24963/ijcai.2025/362"
url: "https://ijcai.org/proceedings/2025/362"
pdf: "https://ijcai.org/proceedings/2025/0362.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "3254-3262"
track: "Main Track"
keywords:
  - "Data Mining: DM: Mining graphs"
  - "Machine Learning: ML: Kernel methods"
---

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

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

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 3254-3262. DOI: [10.24963/ijcai.2025/362](https://doi.org/10.24963/ijcai.2025/362)

## 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.