Unsupervised graph-level representation learning with hierarchical contrasts

计算机科学 图形 理论计算机科学 人工智能 判别式 特征学习
作者
Wei Ju,Yiyang Gu,Xiao Luo,Yifan Wang,Haochen Yuan,Huasong Zhong,Ming Zhang
出处
期刊:Neural Networks [Elsevier BV]
卷期号:158: 359-368 被引量:44
标识
DOI:10.1016/j.neunet.2022.11.019
摘要

Unsupervised graph-level representation learning has recently shown great potential in a variety of domains, ranging from bioinformatics to social networks. Plenty of graph contrastive learning methods have been proposed to generate discriminative graph-level representations recently. They typically design multiple types of graph augmentations and enforce a graph to have consistent representations under different views. However, these techniques mostly neglect the intrinsic hierarchical structure of the graph, resulting in a limited exploration of semantic information for graph representation. Moreover, they often rely on a large number of negative samples to prevent collapsing into trivial solutions, while a great need for negative samples may lead to memory issues during optimization in graph domains. To address the two issues, this paper develops an unsupervised graph-level representation learning framework named Hierarchical Graph Contrastive Learning (HGCL), which investigates the hierarchical structural semantics of a graph at both node and graph levels. Specifically, our HGCL consists of three parts, i.e., node-level contrastive learning, graph-level contrastive learning, and mutual contrastive learning to capture graph semantics hierarchically. Furthermore, the Siamese network and momentum update are further involved to release the demand for excessive negative samples. Finally, the experimental results on both benchmark datasets for graph classification and large-scale OGB datasets for transfer learning demonstrate that our proposed HGCL significantly outperforms a broad range of state-of-the-art baselines.
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
wys发布了新的文献求助10
刚刚
NexusExplorer应助Sugar采纳,获得10
1秒前
踏实悟空完成签到,获得积分10
1秒前
科研通AI5应助nssm采纳,获得10
1秒前
高田熊完成签到,获得积分10
1秒前
1秒前
LISHAN发布了新的文献求助30
2秒前
小花完成签到 ,获得积分20
2秒前
2秒前
qiuling完成签到,获得积分10
3秒前
天宝完成签到,获得积分10
3秒前
摆烂fish完成签到,获得积分10
3秒前
3秒前
洛洛完成签到,获得积分20
3秒前
4秒前
4秒前
清水完成签到,获得积分10
4秒前
yangcy完成签到 ,获得积分10
4秒前
远山完成签到 ,获得积分10
5秒前
加加油完成签到,获得积分10
6秒前
木木完成签到,获得积分10
6秒前
6秒前
酷波er应助yy14207采纳,获得10
7秒前
黎乐荷发布了新的文献求助10
7秒前
烟花应助wys采纳,获得10
7秒前
火星上代天完成签到,获得积分10
8秒前
负责的靖琪完成签到 ,获得积分10
8秒前
hao发布了新的文献求助10
9秒前
円桑发布了新的文献求助10
9秒前
希望天下0贩的0应助bb采纳,获得10
10秒前
成事在人307完成签到,获得积分10
10秒前
10秒前
10秒前
南安完成签到 ,获得积分10
11秒前
咯咚完成签到 ,获得积分10
11秒前
MTF发布了新的文献求助10
12秒前
12秒前
xuyue发布了新的文献求助10
12秒前
欣喜念桃完成签到,获得积分10
13秒前
Aurorademon发布了新的文献求助10
13秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
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
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
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 3968964
求助须知:如何正确求助?哪些是违规求助? 3513877
关于积分的说明 11170569
捐赠科研通 3249201
什么是DOI,文献DOI怎么找? 1794692
邀请新用户注册赠送积分活动 875297
科研通“疑难数据库(出版商)”最低求助积分说明 804755