GPENs: Graph Data Learning With Graph Propagation-Embedding Networks

嵌入 图嵌入 理论计算机科学 计算机科学 特征学习 图形 拓扑图论 人工智能 电压图 折线图
作者
Bo Jiang,Leiling Wang,Jian Cheng,Jin Tang,Bin Luo
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:34 (8): 3925-3938 被引量:1
标识
DOI:10.1109/tnnls.2021.3120100
摘要

Compact representation of graph data is a fundamental problem in pattern recognition and machine learning area. Recently, graph neural networks (GNNs) have been widely studied for graph-structured data representation and learning tasks, such as graph semi-supervised learning, clustering, and low-dimensional embedding. In this article, we present graph propagation-embedding networks (GPENs), a new model for graph-structured data representation and learning problem. GPENs are mainly motivated by 1) revisiting of traditional graph propagation techniques for graph node context-aware feature representation and 2) recent studies on deeply graph embedding and neural network architecture. GPENs integrate both feature propagation on graph and low-dimensional embedding simultaneously into a unified network using a novel propagation-embedding architecture. GPENs have two main advantages. First, GPENs can be well-motivated and explained from feature propagation and deeply learning architecture. Second, the equilibrium representation of the propagation-embedding operation in GPENs has both exact and approximate formulations, both of which have simple closed-form solutions. This guarantees the compactivity and efficiency of GPENs. Third, GPENs can be naturally extended to multiple GPENs (M-GPENs) to address the data with multiple graph structures. Experiments on various semi-supervised learning tasks on several benchmark datasets demonstrate the effectiveness and benefits of the proposed GPENs and M-GPENs.
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
Z.完成签到,获得积分10
刚刚
壮观以松完成签到,获得积分10
刚刚
量子星尘发布了新的文献求助10
刚刚
2秒前
温暖亦玉发布了新的文献求助10
2秒前
小马过河发布了新的文献求助10
3秒前
怡然的映真完成签到,获得积分10
4秒前
qingsyxuan完成签到,获得积分10
4秒前
5秒前
5秒前
02发布了新的文献求助10
5秒前
hzb发布了新的文献求助10
5秒前
天天快乐应助清璃采纳,获得10
6秒前
HJJHJH发布了新的文献求助10
6秒前
6秒前
Russell发布了新的文献求助10
8秒前
整齐乌发布了新的文献求助10
8秒前
多金完成签到,获得积分10
8秒前
屿溡完成签到,获得积分10
10秒前
10秒前
李红侠发布了新的文献求助10
13秒前
yar应助粥粥采纳,获得10
15秒前
15秒前
smottom应助坦率的含海采纳,获得10
16秒前
Luka完成签到,获得积分10
18秒前
JamesPei应助壮观鞋垫采纳,获得10
19秒前
20秒前
20秒前
魏煜佳完成签到,获得积分10
20秒前
开朗山水完成签到 ,获得积分10
22秒前
Oracle发布了新的文献求助10
22秒前
23秒前
水电费发布了新的文献求助10
24秒前
24秒前
LF应助xiaofeiyan采纳,获得10
26秒前
27秒前
SciGPT应助摆烂小子采纳,获得10
27秒前
cwt完成签到,获得积分10
29秒前
邓权发布了新的文献求助10
30秒前
善学以致用应助酷酷妙梦采纳,获得10
36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
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
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 3971469
求助须知:如何正确求助?哪些是违规求助? 3516210
关于积分的说明 11181332
捐赠科研通 3251376
什么是DOI,文献DOI怎么找? 1795810
邀请新用户注册赠送积分活动 876051
科研通“疑难数据库(出版商)”最低求助积分说明 805245