Second-Order Global Attention Networks for Graph Classification and Regression | |
Hu Fenyu1,2![]() ![]() ![]() ![]() ![]() ![]() | |
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 | 否 |
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 |
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。
修改评论