Attention-based stackable graph convolutional network for multi-view learning

计算机科学 图形 利用 人工智能 平滑的 理论计算机科学 机器学习 计算机安全 计算机视觉
作者
Zhiyong Xu,Weibin Chen,Ying Zou,Zihan Fang,Shiping Wang
出处
期刊:Neural Networks [Elsevier BV]
卷期号:180: 106648-106648
标识
DOI:10.1016/j.neunet.2024.106648
摘要

In multi-view learning, graph-based methods like Graph Convolutional Network (GCN) are extensively researched due to effective graph processing capabilities. However, most GCN-based methods often require complex preliminary operations such as sparsification, which may bring additional computation costs and training difficulties. Additionally, as the number of stacking layers increases in most GCN, over-smoothing problem arises, resulting in ineffective utilization of GCN capabilities. In this paper, we propose an attention-based stackable graph convolutional network that captures consistency across views and combines attention mechanism to exploit the powerful aggregation capability of GCN to effectively mitigate over-smoothing. Specifically, we introduce node self-attention to establish dynamic connections between nodes and generate view-specific representations. To maintain cross-view consistency, a data-driven approach is devised to assign attention weights to views, forming a common representation. Finally, based on residual connectivity, we apply an attention mechanism to the original projection features to generate layer-specific complementarity, which compensates for the information loss during graph convolution. Comprehensive experimental results demonstrate that the proposed method outperforms other state-of-the-art methods in multi-view semi-supervised tasks.
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
lyric应助科研通管家采纳,获得10
刚刚
科研通AI2S应助科研通管家采纳,获得10
刚刚
小蘑菇应助科研通管家采纳,获得10
刚刚
领导范儿应助科研通管家采纳,获得10
刚刚
JamesPei应助科研通管家采纳,获得10
刚刚
Akim应助科研通管家采纳,获得10
刚刚
Chao发布了新的文献求助10
1秒前
1秒前
WangSiwei完成签到,获得积分10
2秒前
舒心靖琪完成签到 ,获得积分10
3秒前
xiaobo完成签到,获得积分10
4秒前
冬瓜发布了新的文献求助10
5秒前
杰杰发布了新的文献求助10
5秒前
123完成签到 ,获得积分10
7秒前
量子星尘发布了新的文献求助10
8秒前
爆米花应助33采纳,获得10
8秒前
nadeem完成签到 ,获得积分10
11秒前
11秒前
XYZ完成签到 ,获得积分10
12秒前
12秒前
13秒前
典雅雨寒发布了新的文献求助10
15秒前
杰杰完成签到,获得积分20
15秒前
ElbingX发布了新的文献求助20
17秒前
土冂足各发布了新的文献求助10
20秒前
wz发布了新的文献求助10
23秒前
cym关闭了cym文献求助
24秒前
25秒前
26秒前
lilei完成签到 ,获得积分10
26秒前
桐桐应助ElbingX采纳,获得20
27秒前
29秒前
30秒前
粗犷的德天完成签到,获得积分10
30秒前
Joker完成签到,获得积分0
31秒前
lp关闭了lp文献求助
32秒前
32秒前
是赵先森呀完成签到 ,获得积分10
33秒前
34秒前
糖拌西红柿完成签到,获得积分10
35秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
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 3976177
求助须知:如何正确求助?哪些是违规求助? 3520366
关于积分的说明 11202970
捐赠科研通 3256899
什么是DOI,文献DOI怎么找? 1798535
邀请新用户注册赠送积分活动 877725
科研通“疑难数据库(出版商)”最低求助积分说明 806516