Multiscale Subgraph Adversarial Contrastive Learning

对抗制 计算机科学 人工智能 自然语言处理
作者
Yanbei Liu,Yu Zhao,Zhitao Xiao,Lei Geng,Xiao Wang,Yanwei Pang,Jerry Chun‐Wei Lin
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:36 (8): 15001-15014 被引量:1
标识
DOI:10.1109/tnnls.2025.3543954
摘要

Graph contrastive learning (GCL), as a typical self-supervised learning paradigm, has been able to achieve promising performance without labels and gradually attracts much attention. Graph-level method aims to learn representations of each graph by contrasting two augmented graphs. Previous studies usually simply apply contrastive learning to keep the embeddings of augmented views from the same anchor graph (positive pairs) close to each other, as well as separate the embeddings of augmented views from different anchor graphs (negative pairs). However, it is well-known that the structure of graph is always complex and multiscale, which gives rise to a fundamental question: after graph augmentation, will the previous assumption still hold in reality? Through experimental analytics, we find that the semantic information of two augmented graphs from the same anchor graph may be not consistent, and whether two augmented graphs are positive or negative sample pairs is highly correlated with the multiscale structure of the graph. Based on this observation, we then propose a multiscale subgraph contrastive learning method, named MSSGCL, which can characterize the fine-grained semantic information. Specifically, we generate global and local views at different scales based on subgraph sampling and construct multiple contrastive relationships according to their semantic associations to provide richer self-supervised information. Furthermore, to further improve the generalization performance of the model, we propose an extended model called MSSGCL++. It adopts an asymmetric structure to avoid pushing semantically similar negative samples far away. We further introduce adversarial training to perturb the augmented view and thus construct a more difficult self-supervised training task. Finally, a min-max saddle point problem is optimized and the "free" strategy is used to speed up the training process. Extensive experiments and parametric analysis on 16 real-world graph classification datasets confirm the effectiveness of our proposed approach. Compared with state of the art (SOTA) method, our method achieves improvements of 2% and 1.6% in unsupervised and transfer learning settings, respectively.
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
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
科研通AI65的应助被卓卓卓采纳,获得10
刚刚
ouoii3完成签到,获得积分10
刚刚
正直无极完成签到,获得积分10
2秒前
heeh发布了新的文献求助10
3秒前
乐鱼发布了新的文献求助10
3秒前
张莹发布了新的文献求助30
3秒前
3秒前
double_manager的应助被Gxt采纳,获得10
3秒前
zyy发布了新的文献求助10
4秒前
4秒前
zan12131发布了新的文献求助30
4秒前
义气傲薇发布了新的文献求助10
5秒前
6秒前
6秒前
helping完成签到 ,获得积分10
6秒前
苏邑发布了新的文献求助10
6秒前
长风赴宴完成签到 ,获得积分10
6秒前
6秒前
6秒前
甜蜜发带完成签到 ,获得积分0
6秒前
7秒前
11完成签到,获得积分10
7秒前
酷炫师发布了新的文献求助10
7秒前
7秒前
Lucas的应助被Humingyu采纳,获得10
7秒前
9秒前
9秒前
Nia发布了新的文献求助10
9秒前
简单山水发布了新的文献求助10
9秒前
小孙大王发布了新的文献求助10
10秒前
10秒前
10秒前
踏实初蓝完成签到,获得积分20
10秒前
科研岗完成签到,获得积分10
10秒前
11秒前
唐唐发布了新的文献求助10
11秒前
xhy完成签到 ,获得积分10
11秒前
ini发布了新的文献求助10
11秒前
yan完成签到,获得积分10
11秒前
风_Feng完成签到,获得积分10
12秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181379
求助须知:如何正确求助?哪些是违规求助? 9571317
关于积分的说明 21817457
捐赠科研通 7777820
什么是DOI,文献DOI怎么找? 3433454
关于科研通互助平台的介绍 2557692
邀请新用户注册赠送积分活动 2479523