CASIA OpenIR  > 模式识别实验室
Second-Order Global Attention Networks for Graph Classification and Regression
Hu Fenyu1,2; Cui Zeyu3; Wu Shu1,2; Liu Qiang1,2; Wu Jinlin1,2; Wang Liang1,2; Tan Tieniu1,2
2022-08
会议名称CAAI International Conference on Artificial Intelligence
会议日期August 27-28, 2022
会议地点Beijing, China
摘要

Graph Neural Networks (GNNs) are powerful to learn representation of graph-structured data, which fuse both attributive and topological information. Prior researches have investigated the expressive power of GNNs by comparing it with Weisfeiler-Lehman algorithm. In spite of having achieved promising performance for the isomorphism test, existing methods assume overly restrictive requirement, which might hinder the performance on other graph-level tasks, e.g., graph classification and graph regression. In this paper, we argue the rationality of adaptively emphasizing important information. We propose a novel global attention module from two levels: channel level and node level. Specifically, we exploit second-order channel correlation to extract more discriminative representations. We validate the effectiveness of the proposed approach through extensive experiments on eight benchmark datasets. The proposed method performs better than the other state-of-the-art methods in graph classification and graph regression tasks. Notably, It achieves 2.7% improvement on DD dataset for graph classification and 7.1% absolute improvement on ZINC dataset for graph regression.

收录类别EI
七大方向——子方向分类机器学习
国重实验室规划方向分类智能计算与学习
是否有论文关联数据集需要存交
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/52324
专题模式识别实验室
通讯作者Wu Shu
作者单位1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.University of Chinese Academy of Sciences, Beijing, China
3.DAMO Academy, Alibaba Group, Hangzhou, China
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Hu Fenyu,Cui Zeyu,Wu Shu,et al. Second-Order Global Attention Networks for Graph Classification and Regression[C],2022.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
cicai-496页.pdf(69424KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Hu Fenyu]的文章
[Cui Zeyu]的文章
[Wu Shu]的文章
百度学术
百度学术中相似的文章
[Hu Fenyu]的文章
[Cui Zeyu]的文章
[Wu Shu]的文章
必应学术
必应学术中相似的文章
[Hu Fenyu]的文章
[Cui Zeyu]的文章
[Wu Shu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: cicai-496页.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。