Meta-path infomax joint structure enhancement for multiplex network representation learning
文献类型：期刊论文
| 作者 | Yuan, Ruiwen1,2; Wu, Yajing1 ; Tang, Yongqiang1; Wang, Junping1,2; Zhang, Wensheng1,2
|
| 刊名 | KNOWLEDGE-BASED SYSTEMS
 |
| 出版日期 | 2023-09-05 |
| 卷号 | 275页码:14 |
| 关键词 | Multiplex network Graph neural network Network representation learning Complementary information Graph structure learning |
| ISSN号 | 0950-7051 |
| DOI | 10.1016/j.knosys.2023.110701 |
| 通讯作者 | Tang, Yongqiang(yongqiang.tang@ia.ac.cn) |
| 英文摘要 | Network representation learning has achieved significant success in homogeneous network data analysis in recent years. Nevertheless, they cannot be directly applied in multiplex networks. To overcome the characteristic of heterogeneity in multiplex networks, several emerging methods utilize the concept of meta-path to denote different types of relations and obtain the node representations for each type of meta-path individually. Despite the remarkable progress, there still exist two important issues in the previous approaches. First, the complementary information between different types of meta-paths that may make the representations more discriminative, is rarely investigated. Second, current studies generally learn multiplex node representations based on the original graph structure, while overlooking the latent relations between nodes. To address the aforementioned issues, in this paper, we propose a novel model with Meta-path Infomax joint Structure Enhancement (MISE) for multiplex network representations. Specifically, we first develop a meta-path infomax mechanism, which maximizes the mutual information between local and global meta-path representations, making the node representation contain more complementary information. Additionally, we propose a graph structure learning module that captures the implicit correlations between nodes to construct the latent graph structure. Such structure enhancement is a simple yet surprisingly effective technique to learn high-quality representations. We sufficiently evaluate the performance of our proposal on both supervised and unsupervised downstream tasks. Comprehensive experimental results show that our MISE achieves a promising boost in performance on a variety of real-world datasets for multiplex network representation learning.& COPY; 2023 Elsevier B.V. All rights reserved. |
| 资助项目 | National Key Researchamp; Development Program of China[2021ZD0201600] ; National Natural Science Foundation of China[62106266] ; National Natural Science Foundation of China[U22B2048] ; National Natural Science Foundation of China[92167109] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001027511400001 |
| 出版者 | ELSEVIER |
| 资助机构 | National Key Researchamp; Development Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/53708]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Tang, Yongqiang |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Yuan, Ruiwen,Wu, Yajing,Tang, Yongqiang,et al. Meta-path infomax joint structure enhancement for multiplex network representation learning[J]. KNOWLEDGE-BASED SYSTEMS,2023,275:14. |
| APA | Yuan, Ruiwen,Wu, Yajing,Tang, Yongqiang,Wang, Junping,&Zhang, Wensheng.(2023).Meta-path infomax joint structure enhancement for multiplex network representation learning.KNOWLEDGE-BASED SYSTEMS,275,14. |
| MLA | Yuan, Ruiwen,et al."Meta-path infomax joint structure enhancement for multiplex network representation learning".KNOWLEDGE-BASED SYSTEMS 275(2023):14. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。