---
title: "HA-SCN: Learning Hierarchical Aligned Subtree Convolutional Networks for Graph Classification"
authors:
  - "Xinya Qin"
  - "Lu Bai"
  - "Lixin Cui"
  - "Ming Li"
  - "Hangyuan Du"
  - "Yue Wang"
  - "Edwin Hancock"
doi: "10.24963/ijcai.2025/361"
url: "https://ijcai.org/proceedings/2025/361"
pdf: "https://ijcai.org/proceedings/2025/0361.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "3245-3253"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Convolutional networks"
  - "Data Mining: DM: Mining graphs"
---

# HA-SCN: Learning Hierarchical Aligned Subtree Convolutional Networks for Graph Classification

Xinya Qin, Lu Bai, Lixin Cui, Ming Li, Hangyuan Du, Yue Wang, Edwin Hancock

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 3245-3253. DOI: [10.24963/ijcai.2025/361](https://doi.org/10.24963/ijcai.2025/361)

## Abstract

In this paper, we propose a Hierarchical Aligned Subtree Convolutional Network (HA-SCN) for graph classification. Our idea is to transform graphs of arbitrary sizes into fixed-sized aligned graphs and construct a normalized K-layer m-ary subtree for each node in the aligned graphs. By sliding convolutional filters over the entire subtree at each node, we define a novel subtree convolution and pooling operation that hierarchically abstracts node-level information. We demonstrate that the proposed HA-SCN model not only realizes the convolution mechanism similar to the Convolutional Neural Networks (CNNs), which have the characteristics of weight sharing and fixed-sized receptive fields, but also effectively mitigates the over-squashing problem. Meanwhile, it establishes the correspondence information between nodes, alleviating the information loss issue. Experimental results on various benchmark graph datasets show that our approach achieves state-of-the-art performance in graph classification tasks.