GraphAIR: Graph representation learning with neighborhood aggregation and interaction
文献类型：期刊论文
| 作者 | Hu, Fenyu1,2 ; Zhu, Yanqiao1,2; Wu, Shu1,2; Huang, Weiran3; Wang, Liang1,2; Tan, Tieniu1,2
|
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2021-04-01 |
| 卷号 | 112页码:11 |
| 关键词 | Graph representation learning Neighborhood aggregation Graph neural networks Neighborhood interaction Node classification Link prediction |
| ISSN号 | 0031-3203 |
| DOI | 10.1016/j.patcog.2020.107745 |
| 通讯作者 | Wu, Shu(shu.wu@nlpr.ia.ac.cn) |
| 英文摘要 | Graph representation learning is of paramount importance for a variety of graph analytical tasks, ranging from node classification to community detection. Recently, graph convolutional networks (GCNs) have been successfully applied for graph representation learning. These GCNs generate node representation by aggregating features from the neighborhoods, which follows the "neighborhood aggregation" scheme. In spite of having achieved promising performance on various tasks, existing GCN-based models have difficulty in well capturing complicated non-linearity of graph data. In this paper, we first theoretically prove that coefficients of the neighborhood interacting terms are relatively small in current models, which explains why GCNs barely outperforms linear models. Then, in order to better capture the complicated non-linearity of graph data, we present a novel GraphAIR framework which models the neighborhood interaction in addition to neighborhood aggregation. Comprehensive experiments conducted on benchmark tasks including node classification and link prediction using public datasets demonstrate the effectiveness of the proposed method. (c) 2020 Elsevier Ltd. All rights reserved. |
| 资助项目 | National Natural Science Foundation of China[61772528] ; National Key Research and Development Program[2018YFB1402600] ; National Key Research and Development Program[2016YFB10010 0 0] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000615938800004 |
| 出版者 | ELSEVIER SCI LTD |
| 资助机构 | National Natural Science Foundation of China ; National Key Research and Development Program |
| 源URL | [http://ir.ia.ac.cn/handle/173211/43196]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Wu, Shu |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China 3.Chinese Univ Hong Kong, Hong Kong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Hu, Fenyu,Zhu, Yanqiao,Wu, Shu,et al. GraphAIR: Graph representation learning with neighborhood aggregation and interaction[J]. PATTERN RECOGNITION,2021,112:11. |
| APA | Hu, Fenyu,Zhu, Yanqiao,Wu, Shu,Huang, Weiran,Wang, Liang,&Tan, Tieniu.(2021).GraphAIR: Graph representation learning with neighborhood aggregation and interaction.PATTERN RECOGNITION,112,11. |
| MLA | Hu, Fenyu,et al."GraphAIR: Graph representation learning with neighborhood aggregation and interaction".PATTERN RECOGNITION 112(2021):11. |
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。