Graph Convolutional Network With Self-Augmented Weights for Semi-Supervised Multi-View Learning

计算机科学 图形 人工智能 卷积神经网络 半监督学习 机器学习 理论计算机科学
作者
Junying Wang,Hongyuan Zhang,Wei Wang,Yuan Yuan
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:: 1-14
标识
DOI:10.1109/tnnls.2024.3456593
摘要

Recently, owing to the effectiveness in exploiting inherent connections between data in different views, graph-based deep learning approaches have gained widespread popularity in semi-supervised multi-view tasks. Generally, the existing approaches fuse the information from different views via the linear or nonlinear weight strategies, which distinguish the importance of different views by attributing their weights between [0, 1] , i.e., some less important views are discarded since assigned with 0 and the pivotal views are not enhanced. However, these view-weighting strategies ignore the complementary information from the less important views. To address this issue, a superior-performing graph convolutional network (GCN) with self-augmented weights is proposed. The proposed self-augmented weight strategy is based on exponential series integration, which preserves the less important views and simultaneously strengthens the key views for multi-view fusion. Specifically, the designed weight strategy can adaptively preserve the complementary information from the less important views by assigning nonzero weights and strengthen the pivotal views by assigning higher weights based on exponential series integration. Besides, to further improve the model performance, an orthogonal constraint layer with a forced orthogonal weight is introduced, which is capable of making the representation more discriminative. Extensive experiments demonstrate the superiority of the proposed 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
大幅提高文件上传限制,最高150M (2024-4-1)

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
Zyq发布了新的文献求助10
刚刚
CipherSage应助符水采纳,获得30
刚刚
桐桐应助wr采纳,获得10
1秒前
1秒前
今我来思发布了新的文献求助10
2秒前
若叶若岚完成签到,获得积分10
3秒前
zzzzzz应助葡萄成熟采纳,获得10
3秒前
4秒前
李爱国应助宗师算个瓢啊采纳,获得10
5秒前
Ava应助Zyq采纳,获得10
5秒前
hopen发布了新的文献求助10
9秒前
mkljl完成签到 ,获得积分10
11秒前
11秒前
12秒前
hrt发布了新的文献求助30
12秒前
12秒前
13秒前
14秒前
14秒前
16秒前
17秒前
18秒前
Orange应助大力翠阳采纳,获得10
18秒前
搁浅完成签到 ,获得积分10
19秒前
科目三应助稳重的羿采纳,获得10
20秒前
刘BOSHI发布了新的文献求助10
20秒前
21秒前
23秒前
ahui完成签到 ,获得积分10
23秒前
lelem关注了科研通微信公众号
23秒前
Khr1stINK完成签到,获得积分10
25秒前
25秒前
Jim luo完成签到,获得积分10
26秒前
26秒前
lm26238完成签到,获得积分10
27秒前
27秒前
柏小霜完成签到 ,获得积分10
27秒前
Akim应助mkljl采纳,获得10
28秒前
28秒前
28秒前
高分求助中
The ACS Guide to Scholarly Communication 2500
Sustainability in Tides Chemistry 2000
Microlepidoptera Palaearctica, Volumes 1 and 3 - 13 (12-Volume Set) [German] 1122
The Data Economy: Tools and Applications 1000
Diamonds: Properties, Synthesis and Applications 800
PraxisRatgeber Mantiden., faszinierende Lauerjäger. – Buch gebraucht kaufen 700
Mantiden - Faszinierende Lauerjäger – Buch gebraucht kaufen 700
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3097793
求助须知:如何正确求助?哪些是违规求助? 2749704
关于积分的说明 7605682
捐赠科研通 2401576
什么是DOI,文献DOI怎么找? 1274203
科研通“疑难数据库(出版商)”最低求助积分说明 616015
版权声明 599016