Multi-level attention pooling for graph neural networks: Unifying graph representations with multiple localities.

导出 LinkOut

翻译打印收藏纠错

作者： Takeshi D,Itoh ^[1] ; Takatomi,Kubo ^[2] ; Kazushi,Ikeda ^[3]

作者单位： Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5 Takayama-Cho, Ikoma, Nara 630-0192, Japan. Electronic address: itoh.takeshi.ik4@is.naist.jp. ^[1] Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5 Takayama-Cho, Ikoma, Nara 630-0192, Japan. Electronic address: takatomi-k@is.naist.jp. ^[2] Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5 Takayama-Cho, Ikoma, Nara 630-0192, Japan. Electronic address: kazushi@is.naist.jp. ^[3]

关键词 Graph neural network (GNN)Graph representation learning (GRL)Multi-level attention pooling (MLAP)Multi-level locality

主题词注意力(Attention);学习(Learning)

DOI 10.1016/j.neunet.2021.11.001

PMID 34808587

发布时间 2021-12-14

翻译满意度评价：

准确一般字义偏差语意偏离译文作用小提交

浏览0

Neural networks

2022年145卷

356-373页

相似文献

中文期刊
外文期刊
学位论文
会议论文

检索历史清除

Multi-level attention pooling for graph neural networks: Unifying graph representations with multiple localities.

Neural networks

相似文献

Neural networks

相关期刊

参考文献：
指定格式：	NoteExpress EndNote RefWorks NoteFirst

检索历史 清除

Multi-level attention pooling for graph neural networks: Unifying graph representations with multiple localities.

Neural networks

相似文献

Neural networks

相关期刊

检索历史清除