已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

GSSA: Pay attention to graph feature importance for GCN via statistical self-attention

计算机科学 特征(语言学) 图形 人工智能 特征学习 节点(物理) 机器学习 卷积神经网络 模式识别(心理学) 理论计算机科学 数据挖掘 语言学 结构工程 工程类 哲学
作者
Zheng Jin,Yan Wang,Wanjun Xu,Zilu Gan,Ping Li,Jiancheng Lv
出处
期刊:Neurocomputing [Elsevier BV]
卷期号:417: 458-470 被引量:11
标识
DOI:10.1016/j.neucom.2020.07.098
摘要

Graph convolutional network (GCN) has been proved to be an effective framework for graph-based semi-supervised learning applications. The core operation block of GCN is the convolutional layer, which enables the network to construct node embeddings by fusing both attributes of nodes and relationships between nodes. Different features or feature interactions inherently have various influences on the convolutional layers. However, there are very limited studies about the impact of feature importance in GCN-related communities. In this work, we attempt to augment convolutional layers in GCNs with statistical attention-based feature importance by modeling the latent interactions of features, which is complementary to the standard GCNs and only needs simple calculations with statistics rather than heavy trainings. To this end, we treat the feature input of each convolutional layer as a separate multi-layer heterogeneous graph, and propose Graph Statistical Self-Attention (GSSA) method to automatically learn the hierarchical structure of feature importance. More specifically, we propose two modules in GSSA, Channel-wise Self-Attention (CSA) to capture the dependencies between feature channels, and Mean-based Self-Attention (MSA) to reweight similarities among features. Aiming at each graph convolutional layer, GSSA can be applied in a "plug and play" way for a wide range of GCN variants. To the best of our knowledge, this is the first implementation that optimizes GCNs from the feature importance perspective. Extensive experiments demonstrate that GSSA can promote existing popular baselines remarkably in semi-supervised node classification tasks. We further employ multiple qualitative evaluations to get deep insights into our method.
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
科研通AI2S应助fairy采纳,获得10
1秒前
2秒前
搜集达人应助科研通管家采纳,获得10
2秒前
Lucas应助科研通管家采纳,获得10
2秒前
Owen应助科研通管家采纳,获得20
2秒前
FIN应助科研通管家采纳,获得30
2秒前
2秒前
3秒前
爱笑映菡完成签到,获得积分10
3秒前
5秒前
Jasper应助fafafa采纳,获得20
6秒前
8秒前
姚琛发布了新的文献求助30
9秒前
9秒前
三十七度医完成签到,获得积分10
10秒前
虚幻友瑶发布了新的文献求助10
10秒前
夜游的鱼完成签到 ,获得积分10
11秒前
RC_Wang发布了新的文献求助10
12秒前
hjkk发布了新的文献求助10
13秒前
13秒前
飞舞伤寒完成签到,获得积分10
15秒前
17秒前
18秒前
19秒前
hjkk完成签到,获得积分10
21秒前
xbx1991发布了新的文献求助10
21秒前
21秒前
22秒前
24秒前
学习。。发布了新的文献求助10
29秒前
PATTOM完成签到,获得积分10
31秒前
情怀应助tiantian采纳,获得20
36秒前
36秒前
Akim应助无辜的秀采纳,获得10
39秒前
ttttsy完成签到 ,获得积分10
39秒前
41秒前
柏林寒冬应助松间蓝雾采纳,获得10
41秒前
42秒前
44秒前
哆啦A梦发布了新的文献求助10
47秒前
高分求助中
The Mother of All Tableaux Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 2400
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Cognitive Neuroscience: The Biology of the Mind (Sixth Edition) 1000
Optimal Transport: A Comprehensive Introduction to Modeling, Analysis, Simulation, Applications 800
Official Methods of Analysis of AOAC INTERNATIONAL 600
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 3959900
求助须知:如何正确求助?哪些是违规求助? 3506106
关于积分的说明 11127978
捐赠科研通 3238061
什么是DOI,文献DOI怎么找? 1789483
邀请新用户注册赠送积分活动 871803
科研通“疑难数据库(出版商)”最低求助积分说明 803021