Heterogeneous Graph Neural Network Model Integrating Attribute Completion and Hierarchical Contrastive Learning

WANG Zuwei; XU Congyuan; WU Tong; DENG Kun

doi:10.11959/j.issn.1000-0801.DXKX260057

您当前的位置：

首页 >

文章列表页 >

Heterogeneous Graph Neural Network Model Integrating Attribute Completion and Hierarchical Contrastive Learning

更新时间：2026-05-11

- Heterogeneous Graph Neural Network Model Integrating Attribute Completion and Hierarchical Contrastive Learning
- Telecommunications Science (2026)
- 作者机构：
  
  1.嘉兴大学信息科学与工程学院, 浙江嘉兴 314001
  2.浙江理工大学计算机科学与技术学院(人工智能学院), 浙江杭州 310018
  3.嘉兴大学全省多模态感知与智能系统重点实验室, 浙江嘉兴 314001
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.DXKX260057
  CLC： TP391
- Received：20 January 2026，
  
  Revised：2026-04-20，
  
  Accepted：22 April 2026，
- 稿件说明：
移动端阅览
WANG Zuwei, XU Congyuan, WU Tong, et al. Heterogeneous Graph Neural Network Model Integrating Attribute Completion and Hierarchical Contrastive Learning[J/OL]. Telecommunications Science, 2026.
DOI：

WANG Zuwei, XU Congyuan, WU Tong, et al. Heterogeneous Graph Neural Network Model Integrating Attribute Completion and Hierarchical Contrastive Learning[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260057.

摘要

针对现有异质图神经网络模型难以兼顾异质图中节点属性缺失及标签信息稀缺的问题，提出一种融合属性补全与层次对比的异质图神经网络模型。该模型首先借助编码器-解码器架构对缺失属性进行端到端重建；其次分别在网络模式低阶视图与元路径高阶视图中编码目标节点，其中低阶聚合引入槽结构以缓解类型语义混叠；随后构建元路径视图内与高低阶视图间的层次化对比目标以协同对齐多尺度表征，并结合细粒度的语义-属性双感知正样本采样策略提升对比信号质量，最终生成高判别性节点嵌入。在多个公开数据集上开展了广泛实验，并与多个基线模型进行对比分析。实验结果表明，节点分类任务中Macro-F1值平均提升0.35%~1.99%，节点聚类任务中归一化互信息(normalized mutual information

NMI)值平均提升1.2%~2.1%，验证了模型的有效性。

Abstract

To address the challenge that existing heterogeneous graph neural network models face in simultaneously handling missing node attributes and limited label availability in heterogeneous graphs

this paper proposes a novel heterogeneous graph neural network model that integrates attribute completion with hierarchical contrastive learning. The model first employs an encoder-decoder architecture to achieve end-to-end reconstruction of missing node attributes. Next

it encodes target nodes by capturing both low-order structural neighborhoods and high-order meta-path semantics

where slot-enhanced aggregation is introduced in the low-order representation to reduce type-related semantic ambiguity. To align multi-scale representations effectively

hierarchical contrastive objectives are established within the meta-path space and across low-order and high-order views

enabling collaborative representation learning. Moreover

a fine-grained semantic-attribute dual-aware strategy is applied for positive sample selection to enhance the quality of contrastive signals

leading to highly discriminative node embeddings. Extensive experiments on multiple public datasets

compared against various baseline models

demonstrate that the proposed method achieves average improvements of 0.35% to 1.99% in Macro-F1 score for node classification and 1.2% to 2.1% in Normalized Mutual Information (NMI) for node clustering

thereby validating its effectiveness.

关键词

Keywords

references

杨帅 , 王瑞琴 , 马辉 . 基于多通道的边学习图卷积网络 [J ] . 电信科学 , 2022 , 38 ( 9 ): 95 - 104 .

YANG S , WANG R Q , MA H . Convolutional Network of Edge Learning Graph Based on Multi-channel [J ] . Telecommunications Science , 2022 , 38 ( 9 ): 95 - 104 .

WANG J C , ZHANG Y , WANG L X , et al . Multitask hypergraph convolutional networks: a heterogeneous traffic prediction framework [J ] . IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 10 ): 18557 - 18567 .

刘亚 , 林明洁 , 曲博 . 图表示学习在网络安全领域的应用研究综述 [J ] . 小型微型计算机系统 , 2023 , 44 ( 3 ): 616 - 628 .

LIU Y , LIN M J , QU B . Survey on graph representation learning in cybersecurity domain [J ] . Journal of Chinese Computer Systems , 2023 , 44 ( 3 ): 616 - 628 .

刘群 , 谭洪胜 , 张优敏 , 等 . 基于元路径的动态异质网络表示学习 [J ] . 电子学报 , 2022 , 50 ( 8 ): 1830 - 1839 .

LIU Q , TAN H S , ZHANG Y M , et al . Dynamic heterogeneous network representation method based on meta-path [J ] . Acta Electronica Sinica , 2022 , 50 ( 8 ): 1830 - 1839 .

安俊秀 , 柳源 , 杨林旺 . 超越同质性假设的双通道属性图聚类 [J ] . 电信科学 , 2025 , 41 ( 01 ): 111 - 124 .

AN J X , LIU Y , YANG L W . Dual-channel attribute graph clustering beyond the homogeneity assumption [J ] . Telecommunications Science , 2025 , 41 ( 01 ): 111 - 124 .

宋凌云 , 刘至臻 , 张炀 , 等 . 基于异构图中多层次图结构的级联图卷积网络 [J ] . 软件学报 , 2024 , 35 ( 11 ): 5179 - 5195 .

SONG L Y , LIU Z Z , ZHANG Y , et al . Cascade Graph Convolution Network Based on Multi-level Graph Structures in Heterogeneous Graph [J ] . Journal of Software , 2024 , 35 ( 11 ): 5179 - 5195 .

JIN D , HUO C , LIANG C , et al . Heterogeneous graph neural network via attribute completion [C ] // Proceedings of the Web Conference 2021 . Ljubljana : ACM , 2021 : 391 - 400 .

YU H , ZHENG Z , XUE Y , et al . Knowledge based attribute completion for heterogeneous graph node classification [J ] . Neurocomputing , 2025 , 619 : 129023 .

ZHU G , ZHU Z , WANG W , et al . Autoac: Towards automated attribute completion for heterogeneous graph neural network [C ] // 2023 IEEE 39th International Conference on Data Engineering (ICDE) . Anaheim : IEEE , 2023 : 2808 - 2821 .

ZHAO Z , LIU Z , WANG Y , et al . RA-HGNN: Attribute completion of heterogeneous graph neural networks based on residual attention mechanism [J ] . Expert Systems with Applications , 2024 , 243 : 122945 .

WANG Z , LI Q , YU D , et al . Heterogeneous graph contrastive multi-view learning [C ] // Proceedings of the 2023 SIAM International Conference on Data Mining (SDM) . Minneapolis : SIAM , 2023 : 136 - 144 .

YU J , GE Q , LI X , et al . Heterogeneous graph contrastive learning with meta-path contexts and adaptively weighted negative samples [J ] . IEEE Transactions on Knowledge and Data Engineering , 2024 , 36 ( 10 ): 5181 - 5193 .

WANG X , LIU N , HAN H , et al . Self-supervised heterogeneous graph neural network with co-contrastive learning [C ] // Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining . Virtual : ACM , 2021 : 1726 - 1736 .

LI M , MENG L , YE Z , et al . Multi-scale Heterogeneous Graph Contrastive Learning [C ] // 2023 IEEE International Conference on Big Data (BigData) . Sorrento : IEEE , 2023 : 4432 - 4441 .

YANG X , YAN M , PAN S , et al . Simple and efficient heterogeneous graph neural network [C ] // Proceedings of the AAAI Conference on Artificial Intelligence . Washington : AAAI Press , 2023 , 37 ( 9 ): 10816 - 10824 .

LI S , GONG J , KE S , et al . Graph Transformer-based Heterogeneous Graph Neural Networks enhanced by multiple meta-path adjacency matrices decomposition [J ] . Neurocomputing , 2025 , 629 : 129604 .

WANG K , YU Y , HUANG C , et al . Heterogeneous graph neural network for attribute completion [J ] . Knowledge-Based Systems , 2022 , 251 : 109171 .

SCHLICHTKRULL M , KIPF T N , BLOEM P , et al . Modeling relational data with graph convolutional networks [C ] // European Semantic Web Conference . Heraklion : Springer , 2018 : 593 - 607 .

KIPF T N , WELLING M . Semi-supervised classification with graph convolutional networks [J ] . arXiv preprint arXiv: 1609.02907 , 2016 .

ZHAO Z , GE Q , CHENG A , et al . HetCAN: A Heterogeneous Graph Cascade Attention Network with Dual-Level Awareness [C ] // Joint European Conference on Machine Learning and Knowledge Discovery in Databases . Vilnius : Springer , 2024 : 57 - 73 .

VELICKOVIC P , CUCURULL G , CASANOVA A , et al . Graph attention networks [J ] . arXiv preprint arXiv: 1710.10903 , 2017 .

WANG X , JI H , SHI C , et al . Heterogeneous graph attention network [C ] // The World Wide Web Conference . San Francisco : ACM , 2019 : 2022 - 2032 .

FU X , ZHANG J , MENG Z , et al . Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding [C ] // Proceedings of the Web Conference 2020 . Taipei : ACM , 2020 : 2331 - 2341 .

YU J , LI X . Heterogeneous graph contrastive learning with meta-path contexts and weighted negative samples [C ] // Proceedings of the 2023 SIAM International Conference on Data Mining (SDM) . Minneapolis : SIAM , 2023 : 37 - 45 .

ZHANG Q , ZHAO Z , ZHOU H , et al . Self-supervised contrastive learning on heterogeneous graphs with mutual constraints of structure and feature [J ] . Information Sciences , 2023 , 640 : 119026 .

ZHAO Z , ZHU Z , LIU Y , et al . Heterogeneous graph contrastive learning with augmentation graph [J ] . IEEE Transactions on Artificial Intelligence , 2024 , 5 ( 10 ): 5100 - 5109 .

WANG Z , YU D , LI Q , et al . SR-HGN: Semantic-and relation-aware heterogeneous graph neural network [J ] . Expert Systems with Applications , 2023 , 224 : 119982 .

XU W , XIA Y , LIU W , et al . SHGNN: Structure-aware heterogeneous graph neural network [J ] . arXiv preprint arXiv: 2112.06244 , 2021 .

LI C , YAN Y , FU J , et al . Hetregat-fc: Heterogeneous residual graph attention network via feature completion [J ] . Information Sciences , 2023 , 632 : 424 - 438 .

MAATEN L , HINTON G . Visualizing data using t-sne [J ] . Journal of Machine Learning Research , 2008 , 9 ( 11 ): 2579 - 2605 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Heterogeneous graph neural network algorithm based on topology information enhancement

Attention aware edge-node exchange graph neural network

Research on human action recognition based on mobile communication network signals

Cross-view contrastive learning and multi-channel hypergraph convolution for session-based recommendation

A decomposable and interpretable cellular network traffic prediction model based on graph convolutional neural network

Related Author

YAO Bowu

DENG Kun

WEI Zhenhua

WU Tong

LIU Xingyan

Ruiqin WANG

Yimin HUANG

Qishun JI

Related Institution

College of Artificial Intelligence, Jiaxing University

Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing University

College of Artificial Intelligence and Information Engineering, East China University of Technology

School of Information Engineering, Huzhou University

Library of Wenzhou University

⁰