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
zokor完成签到 ,获得积分0
1秒前
努力退休小博士完成签到 ,获得积分10
2秒前
橙子完成签到,获得积分10
3秒前
陈补天完成签到 ,获得积分10
4秒前
CipherSage应助慧灰huihui采纳,获得10
5秒前
乐观健柏完成签到,获得积分10
6秒前
8秒前
CodeCraft应助大橙子采纳,获得10
8秒前
量子星尘发布了新的文献求助10
9秒前
jeeya完成签到,获得积分10
10秒前
12秒前
科目三应助科研通管家采纳,获得10
12秒前
科目三应助科研通管家采纳,获得10
12秒前
伦语发布了新的文献求助10
12秒前
顾矜应助科研通管家采纳,获得10
12秒前
xuzj应助科研通管家采纳,获得10
12秒前
xuzj应助科研通管家采纳,获得10
12秒前
12秒前
NexusExplorer应助科研通管家采纳,获得10
12秒前
12秒前
12秒前
丘比特应助科研通管家采纳,获得10
13秒前
yull完成签到,获得积分10
13秒前
小巧书雪完成签到,获得积分10
16秒前
大大怪将军完成签到,获得积分10
17秒前
哈哈哈完成签到 ,获得积分0
17秒前
小怪完成签到,获得积分10
18秒前
爱吃泡芙完成签到,获得积分10
19秒前
白桃战士完成签到,获得积分10
20秒前
22秒前
qingchenwuhou完成签到 ,获得积分10
22秒前
XXX完成签到,获得积分10
23秒前
锡嘻完成签到 ,获得积分10
23秒前
24秒前
彗星入梦完成签到 ,获得积分10
24秒前
恋恋青葡萄完成签到,获得积分10
24秒前
隐形万言完成签到,获得积分10
26秒前
Time完成签到,获得积分10
26秒前
土木研学僧完成签到,获得积分10
27秒前
yjy完成签到 ,获得积分10
27秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
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 4038201
求助须知:如何正确求助?哪些是违规求助? 3575940
关于积分的说明 11373987
捐赠科研通 3305747
什么是DOI,文献DOI怎么找? 1819274
邀请新用户注册赠送积分活动 892662
科研通“疑难数据库(出版商)”最低求助积分说明 815022