GPENs: Graph Data Learning With Graph Propagation-Embedding Networks
文献类型：期刊论文
| 作者 | Jiang, Bo2 ; Wang, Leiling2; Cheng, Jian1; Tang, Jin2; Luo, Bin2
|
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2021-10-26 |
| 页码 | 14 |
| 关键词 | Task analysis Computer architecture Semisupervised learning Deep learning Laplace equations Data models Labeling Graph embedding graph neural networks (GNNs) graph propagation semi-supervised learning |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2021.3120100 |
| 通讯作者 | Tang, Jin(tangjin@ahu.edu.cn) |
| 英文摘要 | Compact representation of graph data is a fundamental problem in pattern recognition and machine learning area. Recently, graph neural networks (GNNs) have been widely studied for graph-structured data representation and learning tasks, such as graph semi-supervised learning, clustering, and low-dimensional embedding. In this article, we present graph propagation-embedding networks (GPENs), a new model for graph-structured data representation and learning problem. GPENs are mainly motivated by 1) revisiting of traditional graph propagation techniques for graph node context-aware feature representation and 2) recent studies on deeply graph embedding and neural network architecture. GPENs integrate both feature propagation on graph and low-dimensional embedding simultaneously into a unified network using a novel propagation-embedding architecture. GPENs have two main advantages. First, GPENs can be well-motivated and explained from feature propagation and deeply learning architecture. Second, the equilibrium representation of the propagation-embedding operation in GPENs has both exact and approximate formulations, both of which have simple closed-form solutions. This guarantees the compactivity and efficiency of GPENs. Third, GPENs can be naturally extended to multiple GPENs (M-GPENs) to address the data with multiple graph structures. Experiments on various semi-supervised learning tasks on several benchmark datasets demonstrate the effectiveness and benefits of the proposed GPENs and M-GPENs. |
| WOS关键词 | LABEL PROPAGATION ; FRAMEWORK |
| 资助项目 | Major Project for New Generation of Artificial Intelligence (AI)[2018AAA0100400] ; National Natural Science Foundation of China[62076004] ; Natural Science Foundation of Anhui Province[2108085Y23] ; Cooperative Research Project Program of Nanjing Artificial Intelligence Chip Research, Institute of Automation, Chinese Academy of Sciences |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000733454400001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Major Project for New Generation of Artificial Intelligence (AI) ; National Natural Science Foundation of China ; Natural Science Foundation of Anhui Province ; Cooperative Research Project Program of Nanjing Artificial Intelligence Chip Research, Institute of Automation, Chinese Academy of Sciences |
| 源URL | [http://ir.ia.ac.cn/handle/173211/46917]  |
| 专题 | 类脑芯片与系统研究 |
| 通讯作者 | Tang, Jin |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Anhui Univ, Anhui Prov Key Lab Multimodal Cognit Computat, Sch Comp Sci & Technol, Hefei 230601, Peoples R China |
| 推荐引用方式 GB/T 7714 | Jiang, Bo,Wang, Leiling,Cheng, Jian,et al. GPENs: Graph Data Learning With Graph Propagation-Embedding Networks[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021:14. |
| APA | Jiang, Bo,Wang, Leiling,Cheng, Jian,Tang, Jin,&Luo, Bin.(2021).GPENs: Graph Data Learning With Graph Propagation-Embedding Networks.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,14. |
| MLA | Jiang, Bo,et al."GPENs: Graph Data Learning With Graph Propagation-Embedding Networks".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021):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。