Simple Contrastive Graph Clustering

计算机科学 聚类分析 预处理器 人工智能 数据挖掘 图形 理论计算机科学 模式识别(心理学) 机器学习 算法
作者
Yue Liu,Xihong Yang,Sihang Zhou,Xinwang Liu,Siwei Wang,Ke Liang,Wenxuan Tu,Liang Li
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:35 (10): 13789-13800 被引量:74
标识
DOI:10.1109/tnnls.2023.3271871
摘要

Contrastive learning has recently attracted plenty of attention in deep graph clustering due to its promising performance. However, complicated data augmentations and time-consuming graph convolutional operations undermine the efficiency of these methods. To solve this problem, we propose a simple contrastive graph clustering (SCGC) algorithm to improve the existing methods from the perspectives of network architecture, data augmentation, and objective function. As to the architecture, our network includes two main parts, that is, preprocessing and network backbone. A simple low-pass denoising operation conducts neighbor information aggregation as an independent preprocessing, and only two multilayer perceptrons (MLPs) are included as the backbone. For data augmentation, instead of introducing complex operations over graphs, we construct two augmented views of the same vertex by designing parameter unshared Siamese encoders and perturbing the node embeddings directly. Finally, as to the objective function, to further improve the clustering performance, a novel cross-view structural consistency objective function is designed to enhance the discriminative capability of the learned network. Extensive experimental results on seven benchmark datasets validate our proposed algorithm's effectiveness and superiority. Significantly, our algorithm outperforms the recent contrastive deep clustering competitors with at least seven times speedup on average. The code of SCGC is released at SCGC. Besides, we share a collection of deep graph clustering, including papers, codes, and datasets at ADGC.
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
静若繁花发布了新的文献求助10
刚刚
刚刚
1秒前
hucaicai给hucaicai的求助进行了留言
1秒前
1秒前
凭栏听雨完成签到,获得积分10
1秒前
天真的不尤完成签到 ,获得积分10
2秒前
2秒前
河豚完成签到,获得积分10
2秒前
3秒前
可靠盼旋发布了新的文献求助10
4秒前
HEIKU应助1234采纳,获得10
4秒前
4秒前
4秒前
丘比特应助多变的卡宾采纳,获得10
4秒前
5秒前
小破网发布了新的文献求助20
5秒前
5秒前
呆萌忆秋完成签到,获得积分10
6秒前
田様应助荆轲刺秦王采纳,获得10
6秒前
LUCKY发布了新的文献求助10
7秒前
Komorebi发布了新的文献求助10
7秒前
131发布了新的文献求助50
8秒前
8秒前
听风发布了新的文献求助50
9秒前
9秒前
123456杯可乐完成签到,获得积分20
9秒前
自由山槐发布了新的文献求助100
9秒前
cdercder应助梨涡远点啊采纳,获得10
10秒前
标致咖啡发布了新的文献求助10
11秒前
xinzhuoyang发布了新的文献求助10
11秒前
11秒前
12秒前
知性的剑身完成签到,获得积分10
12秒前
NexusExplorer应助qitan采纳,获得10
12秒前
12发布了新的文献求助20
13秒前
xn201120完成签到 ,获得积分10
13秒前
小鱼干完成签到,获得积分10
14秒前
斯文败类应助海藻采纳,获得10
14秒前
14秒前
高分求助中
Technologies supporting mass customization of apparel: A pilot project 600
Chinesen in Europa – Europäer in China: Journalisten, Spione, Studenten 500
Arthur Ewert: A Life for the Comintern 500
China's Relations With Japan 1945-83: The Role of Liao Chengzhi // Kurt Werner Radtke 500
Two Years in Peking 1965-1966: Book 1: Living and Teaching in Mao's China // Reginald Hunt 500
Understanding Interaction in the Second Language Classroom Context 300
Essentials of Pharmacoeconomics: Health Economics and Outcomes Research 3rd Edition. by Karen Rascati 300
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 3809722
求助须知:如何正确求助?哪些是违规求助? 3354237
关于积分的说明 10369760
捐赠科研通 3070510
什么是DOI,文献DOI怎么找? 1686393
邀请新用户注册赠送积分活动 810922
科研通“疑难数据库(出版商)”最低求助积分说明 766433