Open Access

ARTICLE

D2GSL: Self-Supervised Dual-Layer Structure-Driven Graph Structure Learning

Juncheng Zhang^1,2, Xuhao Wei^1,2, Xiaolei Gu³, Haixing Zhao^4,*, Zhonglin Ye^1,2,5,*

1 School of Computer, Qinghai Normal University, Xining, China
2 State Key Laboratory of Tibetan Intelligent, Xining, China
3 Qinghai Provincial Public Security Department, Xining, China
4 College of Intelligent Science and Engineering, Qinghai Minzu University, Xining, China
5 Graduate School of Engineering, Nagasaki Institute of Applied Science, Nagasaki, Japan

* Corresponding Authors: Haixing Zhao. Email: ; Zhonglin Ye. Email:

Computer Modeling in Engineering & Sciences 2026, 148(2), 37 https://doi.org/10.32604/cmes.2026.083131

Received 30 March 2026; Accepted 17 July 2026; Issue published 28 August 2026

Abstract

Graph structure learning depends heavily on the integrity and reliability of graph data. However, real-world graphs often contain noise, missing information, and bias, thereby limiting the expressive capacity of existing models. Single-layer structure learning methods fail to simultaneously capture local interactions and the global structure. Furthermore, they rely excessively on high-quality labeled data, leading to label scarcity issues and high annotation costs. To address these challenges, we propose a self-supervised dual-layer structure-driven graph structure learning method, termed D2GSL. Specifically, D2GSL constructs a semantic similarity channel and a spectral feature channel to model node relationships from both local semantic and global spectral views. It introduces a hyperadjacency matrix that explicitly models inter-layer node correspondences and enables joint structural reconstruction across channels. The framework further applies structural reconstruction constraints and adopts a contrastive learning mechanism to enhance structural representations in a self-supervised setting. Comprehensive experimental results demonstrate that D2GSL consistently outperforms mainstream baseline models on public benchmark datasets and exhibits remarkable efficacy under label-scarcity conditions.

---

Keywords

---