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
刚刚
x跳完成签到,获得积分10
刚刚
研友_xLOMQZ完成签到,获得积分0
2秒前
2秒前
Sunsetz发布了新的文献求助10
2秒前
田盐盐发布了新的文献求助10
2秒前
勤劳的老九应助Cwx2020采纳,获得10
3秒前
3秒前
请叫我风吹麦浪应助wwmmyy采纳,获得10
5秒前
wei发布了新的文献求助10
6秒前
深情安青应助pinkangel采纳,获得10
6秒前
6秒前
zh完成签到,获得积分10
6秒前
英姑应助何毅采纳,获得10
7秒前
领导范儿应助丙烯酸树脂采纳,获得10
8秒前
huayi发布了新的文献求助10
9秒前
liu发布了新的文献求助10
9秒前
Zzz完成签到,获得积分10
9秒前
10秒前
快乐再出发完成签到,获得积分10
11秒前
12秒前
隐形曼青应助iuv采纳,获得10
13秒前
zty568发布了新的文献求助10
13秒前
wei完成签到,获得积分10
13秒前
13秒前
scale发布了新的文献求助10
14秒前
xiaowuge完成签到 ,获得积分10
14秒前
15秒前
典雅碧空应助wawaeryu采纳,获得10
16秒前
16秒前
Gin完成签到 ,获得积分10
16秒前
嘟噜发布了新的文献求助50
16秒前
扎心发布了新的文献求助10
17秒前
张两丰完成签到,获得积分10
18秒前
19秒前
爆米花应助liu采纳,获得10
19秒前
BING发布了新的文献求助10
20秒前
iuv发布了新的文献求助10
20秒前
20秒前
何毅发布了新的文献求助10
21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) 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 3971754
求助须知:如何正确求助?哪些是违规求助? 3516395
关于积分的说明 11182513
捐赠科研通 3251618
什么是DOI,文献DOI怎么找? 1795980
邀请新用户注册赠送积分活动 876180
科研通“疑难数据库(出版商)”最低求助积分说明 805358