HGNN−BRFE: Heterogeneous Graph Neural Network Model Based on Region Feature Extraction
Open Access
- 13 November 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (22) , 4447
Abstract
With the strong capability of heterogeneous graphs in accurately modeling various types of nodes and their interactions, they have gradually become a research hotspot, promoting the rapid development of the field of heterogeneous graph neural networks (HGNNs). However, most existing HGNN models rely on meta−paths for feature extraction, which can only utilize part of the data from the graph for training and learning. This not only limits the data generalization ability of deep learning models but also affects the application effect of data−driven adaptive technologies. In response to this challenge, this study proposes a new model—heterogeneous graph neural network based on regional feature extraction (HGNN−BRFE). This model enhances performance through an “extraction−fusion” strategy in three key aspects: first, it efficiently extracts features of neighboring nodes of the same type according to specific regions; second, it effectively fuses information from different regions and hierarchical neighbors using attention mechanisms; third, it specially designs a process for feature extraction and fusion targeting heterogeneous type nodes, ensuring that the rich semantic and heterogeneity information within the heterogeneous graph is retained while maintaining the node’s own characteristics during the node embedding process to prevent the loss of its own features and potential over−smoothing issues. Experimental results show that HGNN−BRFE achieves a performance improvement of 1–3% over existing methods on classification tasks across multiple real−world datasets.Keywords
Funding Information
- National Key Research and Development Program of China (2022ZD0119501, 52374221, ZR2022MF288, ZR2023MF097, ts20190936)
- National Natural Science Foundation of China (2022ZD0119501, 52374221, ZR2022MF288, ZR2023MF097, ts20190936)
- Sci. & Tech. Development Fund of Shandong Province of China (2022ZD0119501, 52374221, ZR2022MF288, ZR2023MF097, ts20190936)
- the Taishan Scholar Program of Shandong Province (2022ZD0119501, 52374221, ZR2022MF288, ZR2023MF097, ts20190936)
This publication has 20 references indexed in Scilit:
- Heterogeneous graph neural network for attribute completionKnowledge-Based Systems, 2022
- Interpretable and Efficient Heterogeneous Graph Convolutional NetworkIEEE Transactions on Knowledge and Data Engineering, 2021
- Heterogeneous Graph Propagation NetworkIEEE Transactions on Knowledge and Data Engineering, 2021
- Understanding deep learning (still) requires rethinking generalizationCommunications of the ACM, 2021
- Relation Structure-Aware Heterogeneous Graph Neural Network2019
- Heterogeneous Graph Neural Network2019
- Modeling Relational Data with Graph Convolutional Networks2018
- HIN2Vec2017
- Structural Deep Network Embedding2016
- Deep learning in neural networks: An overviewNeural Networks, 2015