Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network
Heterogeneous Information Networks (HINs) are ubiquitous in our daily life, as they can describe complex interactions among various types of objects. Heterogeneous information network embedding aims to project the network elements of HINs into low-dimensional node representation vectors, which can f...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9458265/ |
| _version_ | 1811210308739399680 |
|---|---|
| author | Meng Cao Jinliang Yuan Ming Xu Hualei Yu Chongjun Wang |
| author_facet | Meng Cao Jinliang Yuan Ming Xu Hualei Yu Chongjun Wang |
| author_sort | Meng Cao |
| collection | DOAJ |
| description | Heterogeneous Information Networks (HINs) are ubiquitous in our daily life, as they can describe complex interactions among various types of objects. Heterogeneous information network embedding aims to project the network elements of HINs into low-dimensional node representation vectors, which can facilitate effective analyze of HINs. To learn appropriate HIN embeddings, most existing methods usually adopt meta-paths to capture the heterogeneous semantic information, which require domain knowledge and trial-and-error to find suitable meta-paths. Besides, most existing methods fail to preserve high-order local structural information, and pay little attention to the implicit semantics in HINs. In this paper, we propose a local structural aware heterogeneous information network embedding model named LSA-HNE. Specifically, we first design a relational self-attention graph neural network model to aggregate heterogeneous information and automatically extract semantic similarity without using meta-paths. In addition, we employ a biased random walk based sampling method to extract the local structural information and preserve the implicit semantics in HINs. The experiments conducted on four real-world datasets show that our proposed model is effective compared with the state-of-the-art methods. |
| first_indexed | 2024-04-12T04:53:27Z |
| format | Article |
| id | doaj.art-62f8d5243574466ab3b6bfdafccfe2bd |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T04:53:27Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-62f8d5243574466ab3b6bfdafccfe2bd2022-12-22T03:47:14ZengIEEEIEEE Access2169-35362021-01-019883018831210.1109/ACCESS.2021.30900559458265Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural NetworkMeng Cao0https://orcid.org/0000-0002-1008-5509Jinliang Yuan1Ming Xu2Hualei Yu3Chongjun Wang4Department of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, ChinaDepartment of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, ChinaDepartment of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, ChinaDepartment of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, ChinaDepartment of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, ChinaHeterogeneous Information Networks (HINs) are ubiquitous in our daily life, as they can describe complex interactions among various types of objects. Heterogeneous information network embedding aims to project the network elements of HINs into low-dimensional node representation vectors, which can facilitate effective analyze of HINs. To learn appropriate HIN embeddings, most existing methods usually adopt meta-paths to capture the heterogeneous semantic information, which require domain knowledge and trial-and-error to find suitable meta-paths. Besides, most existing methods fail to preserve high-order local structural information, and pay little attention to the implicit semantics in HINs. In this paper, we propose a local structural aware heterogeneous information network embedding model named LSA-HNE. Specifically, we first design a relational self-attention graph neural network model to aggregate heterogeneous information and automatically extract semantic similarity without using meta-paths. In addition, we employ a biased random walk based sampling method to extract the local structural information and preserve the implicit semantics in HINs. The experiments conducted on four real-world datasets show that our proposed model is effective compared with the state-of-the-art methods.https://ieeexplore.ieee.org/document/9458265/Graph neural networkheterogeneous information networknetwork embeddingsocial network analysis |
| spellingShingle | Meng Cao Jinliang Yuan Ming Xu Hualei Yu Chongjun Wang Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network IEEE Access Graph neural network heterogeneous information network network embedding social network analysis |
| title | Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network |
| title_full | Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network |
| title_fullStr | Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network |
| title_full_unstemmed | Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network |
| title_short | Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network |
| title_sort | local structural aware heterogeneous information network embedding based on relational self attention graph neural network |
| topic | Graph neural network heterogeneous information network network embedding social network analysis |
| url | https://ieeexplore.ieee.org/document/9458265/ |
| work_keys_str_mv | AT mengcao localstructuralawareheterogeneousinformationnetworkembeddingbasedonrelationalselfattentiongraphneuralnetwork AT jinliangyuan localstructuralawareheterogeneousinformationnetworkembeddingbasedonrelationalselfattentiongraphneuralnetwork AT mingxu localstructuralawareheterogeneousinformationnetworkembeddingbasedonrelationalselfattentiongraphneuralnetwork AT hualeiyu localstructuralawareheterogeneousinformationnetworkembeddingbasedonrelationalselfattentiongraphneuralnetwork AT chongjunwang localstructuralawareheterogeneousinformationnetworkembeddingbasedonrelationalselfattentiongraphneuralnetwork |