---
title: "Similarity-Guided Structural Matching Learning for Graph Dataset Condensation"
authors:
  - "Yiyang Zhang"
  - "Yutong Ye"
  - "Yingbo Zhou"
  - "Nan Zhang"
  - "Xiang Lian"
  - "Mingsong Chen"
doi: "10.24963/ijcai.2026/597"
url: "https://ijcai.org/proceedings/2026/597"
pdf: "https://ijcai.org/proceedings/2026/0597.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5360-5368"
track: "Main Track"
keywords:
  - "Machine Learning: Applications"
---

# Similarity-Guided Structural Matching Learning for Graph Dataset Condensation

Yiyang Zhang, Yutong Ye, Yingbo Zhou, Nan Zhang, Xiang Lian, Mingsong Chen

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5360-5368. DOI: [10.24963/ijcai.2026/597](https://doi.org/10.24963/ijcai.2026/597)

## Abstract

As graph repositories grow in scale and diversity, training Graph Neural Networks (GNNs) becomes computationally demanding. However, existing graph condensation methods often fail to retain the intrinsic structural patterns of the original graphs, which are essential in graph-based learning. Therefore, these methods suffer from limited performance and poor generalization in downstream tasks due to the loss of structural information. To address this, we propose Similarity-guided Structural Matching Learning for Graph Dataset Condensation (SSGDC), which efficiently reduces repository size while maintaining both task performance and structural information. Our approach introduces a similarity-based graph selector to identify high-quality subsets for condensation. The condensed graphs are optimized using a dual-objective loss that combines gradient-matching for task alignment with a metric-learning loss for structural preservation within the selected subset. This ensures that the condensed dataset retains both task-relevant information and the essential relational topology that supports GNN training and enhances generalization. Experiments demonstrate that our method achieves higher accuracy and better structure retention across varying condensation ratios, highlighting the critical role of structural preservation in graph dataset condensation.