Graph Contrastive Learning with Adaptive Augmentation

计算机科学 图形 理论计算机科学 特征学习 人工智能 图表布局 机器学习 图形绘制
作者
Yanqiao Zhu,Yichen Xu,Feng Yu,Qiang Liu,Shu Wu,Liang Wang
出处
期刊:Cornell University - arXiv 卷期号:: 2069-2080 被引量:158
标识
DOI:10.1145/3442381.3449802
摘要

Recently, contrastive learning (CL) has emerged as a successful method for unsupervised graph representation learning. Most graph CL methods first perform stochastic augmentation on the input graph to obtain two graph views and maximize the agreement of representations in the two views. Despite the prosperous development of graph CL methods, the design of graph augmentation schemes -- a crucial component in CL -- remains rarely explored. We argue that the data augmentation schemes should preserve intrinsic structures and attributes of graphs, which will force the model to learn representations that are insensitive to perturbation on unimportant nodes and edges. However, most existing methods adopt uniform data augmentation schemes, like uniformly dropping edges and uniformly shuffling features, leading to suboptimal performance. In this paper, we propose a novel graph contrastive representation learning method with adaptive augmentation that incorporates various priors for topological and semantic aspects of the graph. Specifically, on the topology level, we design augmentation schemes based on node centrality measures to highlight important connective structures. On the node attribute level, we corrupt node features by adding more noise to unimportant node features, to enforce the model to recognize underlying semantic information. We perform extensive experiments of node classification on a variety of real-world datasets. Experimental results demonstrate that our proposed method consistently outperforms existing state-of-the-art baselines and even surpasses some supervised counterparts, which validates the effectiveness of the proposed contrastive framework with adaptive augmentation.
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
JingyuHuang发布了新的文献求助10
刚刚
神说要有光完成签到,获得积分10
1秒前
阁下久等了完成签到 ,获得积分10
1秒前
1秒前
Setlla完成签到 ,获得积分10
2秒前
kilig发布了新的文献求助20
3秒前
小鱼儿完成签到,获得积分10
4秒前
丽丽发布了新的文献求助30
4秒前
6秒前
韩瑶发布了新的文献求助10
6秒前
8秒前
执着银耳汤完成签到,获得积分10
9秒前
烟花应助科研通管家采纳,获得10
10秒前
Cherish应助科研通管家采纳,获得10
10秒前
科研通AI5应助科研通管家采纳,获得10
10秒前
科研通AI2S应助科研通管家采纳,获得10
10秒前
Huuu完成签到,获得积分10
10秒前
星辰大海应助科研通管家采纳,获得10
10秒前
NexusExplorer应助科研通管家采纳,获得10
10秒前
深情安青应助科研通管家采纳,获得10
10秒前
cherry111发布了新的文献求助10
10秒前
马库拉格发布了新的文献求助10
11秒前
务实豪发布了新的文献求助10
13秒前
甜心肖宝完成签到 ,获得积分10
13秒前
脑洞疼应助Liza0711采纳,获得30
13秒前
5160完成签到,获得积分10
13秒前
Akim应助Fanfan采纳,获得10
13秒前
Lucas应助Echo采纳,获得10
15秒前
15秒前
15秒前
15秒前
今后应助务实豪采纳,获得10
17秒前
19秒前
Yolen LI完成签到,获得积分10
20秒前
安辰发布了新的文献求助10
20秒前
小蘑菇应助Season采纳,获得10
21秒前
丽丽完成签到,获得积分10
21秒前
叮叮咚咚完成签到,获得积分10
22秒前
22秒前
Liza0711完成签到,获得积分20
23秒前
高分求助中
Les Mantodea de Guyane Insecta, Polyneoptera 2500
Technologies supporting mass customization of apparel: A pilot project 450
China—Art—Modernity: A Critical Introduction to Chinese Visual Expression from the Beginning of the Twentieth Century to the Present Day 430
A Field Guide to the Amphibians and Reptiles of Madagascar - Frank Glaw and Miguel Vences - 3rd Edition 400
China Gadabouts: New Frontiers of Humanitarian Nursing, 1941–51 400
The Healthy Socialist Life in Maoist China, 1949–1980 400
Walking a Tightrope: Memories of Wu Jieping, Personal Physician to China's Leaders 400
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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3789633
求助须知:如何正确求助?哪些是违规求助? 3334559
关于积分的说明 10270626
捐赠科研通 3050998
什么是DOI,文献DOI怎么找? 1674381
邀请新用户注册赠送积分活动 802549
科研通“疑难数据库(出版商)”最低求助积分说明 760761