Graph Multi-Convolution and Attention Pooling for Graph Classification

计算机科学 联营 人工智能 图形 电压图 图形属性 折线图 理论计算机科学
作者
Yuhua Xu,Junli Wang,Mingjian Guang,Changjun Jiang
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:46 (12): 10546-10557
标识
DOI:10.1109/tpami.2024.3443253
摘要

Many studies have achieved excellent performance in analyzing graph-structured data. However, learning graph-level representations for graph classification is still a challenging task. Existing graph classification methods usually pay less attention to the fusion of node features and ignore the effects of different-hop neighborhoods on nodes in the graph convolution process. Moreover, they discard some nodes directly during the graph pooling process, resulting in the loss of graph information. To tackle these issues, we propose a new Graph Multi-Convolution and Attention Pooling based graph classification method (GMCAP). Specifically, the designed Graph Multi-Convolution (GMConv) layer explicitly fuses node features learned from different perspectives. The proposed weight-based aggregation module combines the outputs of all GMConv layers, for adaptively exploiting the information over different-hop neighborhoods to generate informative node representations. Furthermore, the designed Local information and Global Attention based Pooling (LGAPool) utilizes the local information of a graph to select several important nodes and aggregates the information of unselected nodes to the selected ones by a global attention mechanism when reconstructing a pooled graph, thus effectively reducing the loss of graph information. Extensive experiments show that GMCAP outperforms the state-of-the-art methods on graph classification tasks, demonstrating that GMCAP can learn graph-level representations effectively.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
星辰完成签到,获得积分10
2秒前
3秒前
3秒前
3秒前
4秒前
6秒前
6666发布了新的文献求助10
8秒前
无限雨南发布了新的文献求助10
8秒前
EgoElysia完成签到,获得积分10
8秒前
敏感雅香发布了新的文献求助10
9秒前
归尘发布了新的文献求助150
10秒前
zumri发布了新的文献求助10
10秒前
jia完成签到,获得积分10
12秒前
13秒前
13秒前
hino发布了新的文献求助10
13秒前
共享精神应助6666采纳,获得10
15秒前
shower_009完成签到,获得积分10
16秒前
18秒前
在水一方应助哈哈采纳,获得10
19秒前
19秒前
纯真追命完成签到 ,获得积分10
19秒前
19秒前
20秒前
咚咚锵完成签到,获得积分10
20秒前
20秒前
包容的琦发布了新的文献求助30
23秒前
梦里繁花发布了新的文献求助10
23秒前
Wang完成签到,获得积分10
25秒前
weilanhaian完成签到,获得积分10
25秒前
26秒前
蒋雪琴完成签到 ,获得积分10
26秒前
wjw发布了新的文献求助10
27秒前
28秒前
FashionBoy应助聪慧的正豪采纳,获得10
29秒前
29秒前
李长印发布了新的文献求助10
30秒前
30秒前
weilanhaian发布了新的文献求助10
31秒前
32秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3988868
求助须知:如何正确求助?哪些是违规求助? 3531255
关于积分的说明 11253071
捐赠科研通 3269858
什么是DOI,文献DOI怎么找? 1804822
邀请新用户注册赠送积分活动 881994
科研通“疑难数据库(出版商)”最低求助积分说明 809035