CASIA OpenIR  > 智能感知与计算研究中心
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
Conference NameCAAI International Conference on Artificial Intelligence
Conference DateAugust 27-28, 2022
Conference PlaceBeijing, China
Abstract

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.

Indexed ByEI
Sub direction classification机器学习
planning direction of the national heavy laboratory智能计算与学习
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/52324
Collection智能感知与计算研究中心
Corresponding AuthorWu Shu
Affiliation1.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
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Hu Fenyu,Cui Zeyu,Wu Shu,et al. Second-Order Global Attention Networks for Graph Classification and Regression[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
cicai-496页.pdf(69424KB)会议论文 开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hu Fenyu]'s Articles
[Cui Zeyu]'s Articles
[Wu Shu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hu Fenyu]'s Articles
[Cui Zeyu]'s Articles
[Wu Shu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hu Fenyu]'s Articles
[Cui Zeyu]'s Articles
[Wu Shu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: cicai-496页.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.