A Re-evaluation of Deep Learning Methods for Attributed Graph Clustering

计算机科学 聚类分析 图形 聚类系数 数据挖掘 图划分 水准点(测量) 人工智能 机器学习 理论计算机科学 大地测量学 地理
作者
Xinying Lai,Dingming Wu,Christian S. Jensen,Kezhong Lu
标识
DOI:10.1145/3583780.3614768
摘要

Attributed graph clustering aims to partition the nodes in a graph into groups such that the nodes in the same group are close in terms of graph proximity and also have similar attribute values. Recently, deep learning methods have achieved state-of-the-art clustering performance. However, the effectiveness of existing methods remains unclear due to two reasons. First, the datasets used for evaluation do not support fully the goal of attributed graph clustering. The category labels of nodes are only relevant to node attributes, and nodes with the same category label are often distant in the graph. Second, existing methods for the attributed graph clustering are complex and consist of several components. There is lack of comparisons of methods composed of different components from existing methods. This study proposes six benchmark datasets that support better the goal of attributed graph clustering and reports the performance of existing representative methods. Given that existing methods leave room for improvement on the proposed benchmark datasets, we systematically analyze five aspects of existing methods: encoded information, training networks, fusion mechanisms, loss functions, and clustering result generation. Based on these aspects, we decompose existing methods into modules and evaluate the performance of reconfigured methods based on these modules. According to the experimental results on the proposed benchmark datasets, we identify two promising configurations: (i) taking the attribute matrix as input to a graph convolutional network and (ii) layer-wise linear fusing deep neural network and graph attention network. And we also find that complex loss function fails to improve the clustering performance.
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
阳光的无颜完成签到 ,获得积分10
刚刚
刚刚
丘比特应助有魅力的猫咪采纳,获得10
刚刚
zzz发布了新的文献求助10
1秒前
1秒前
恐龙让梨完成签到,获得积分20
1秒前
伶俐绿柏完成签到 ,获得积分10
2秒前
liuyunhao7207发布了新的文献求助10
2秒前
2秒前
勤奋旭尧发布了新的文献求助10
2秒前
3秒前
田様应助牛牛采纳,获得10
3秒前
科目三应助诺之采纳,获得10
3秒前
LIN123发布了新的文献求助10
4秒前
充电宝应助Cathy采纳,获得10
4秒前
科研一点通完成签到 ,获得积分10
4秒前
4秒前
wljn发布了新的文献求助10
4秒前
等待半烟发布了新的文献求助10
4秒前
xinlixi完成签到,获得积分0
5秒前
5秒前
6秒前
6秒前
magic_sweets发布了新的文献求助10
6秒前
7秒前
8秒前
Jasper应助Stroeve采纳,获得10
9秒前
啦啦啦啦完成签到,获得积分10
9秒前
Kikua发布了新的文献求助10
10秒前
等待半烟完成签到,获得积分10
10秒前
qqq发布了新的文献求助10
11秒前
wljn完成签到,获得积分10
12秒前
12秒前
yu完成签到 ,获得积分10
12秒前
cqy发布了新的文献求助10
13秒前
诺之发布了新的文献求助10
15秒前
hua应助孜然炸鸡排采纳,获得10
16秒前
小绿茶完成签到 ,获得积分10
17秒前
FashionBoy应助Jerna采纳,获得10
18秒前
安静的雨完成签到,获得积分10
19秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3988786
求助须知:如何正确求助?哪些是违规求助? 3531116
关于积分的说明 11252493
捐赠科研通 3269766
什么是DOI,文献DOI怎么找? 1804771
邀请新用户注册赠送积分活动 881870
科研通“疑难数据库(出版商)”最低求助积分说明 809021