Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning

计算机科学 编码 图形 理论计算机科学 聚类分析 特征学习 节点(物理) 聚类系数 数据挖掘 人工智能 生物化学 结构工程 基因 工程类 化学
作者
Costas Mavromatis,George Karypis
出处
期刊:Cornell University - arXiv 被引量:14
标识
DOI:10.48550/arxiv.2009.06946
摘要

Unsupervised (or self-supervised) graph representation learning is essential to facilitate various graph data mining tasks when external supervision is unavailable. The challenge is to encode the information about the graph structure and the attributes associated with the nodes and edges into a low dimensional space. Most existing unsupervised methods promote similar representations across nodes that are topologically close. Recently, it was shown that leveraging additional graph-level information, e.g., information that is shared among all nodes, encourages the representations to be mindful of the global properties of the graph, which greatly improves their quality. However, in most graphs, there is significantly more structure that can be captured, e.g., nodes tend to belong to (multiple) clusters that represent structurally similar nodes. Motivated by this observation, we propose a graph representation learning method called Graph InfoClust (GIC), that seeks to additionally capture cluster-level information content. These clusters are computed by a differentiable K-means method and are jointly optimized by maximizing the mutual information between nodes of the same clusters. This optimization leads the node representations to capture richer information and nodal interactions, which improves their quality. Experiments show that GIC outperforms state-of-art methods in various downstream tasks (node classification, link prediction, and node clustering) with a 0.9% to 6.1% gain over the best competing approach, on average.

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
隐形曼青应助murry123采纳,获得10
刚刚
ANG完成签到 ,获得积分10
刚刚
1秒前
李嘉欣发布了新的文献求助10
2秒前
2秒前
lascqy完成签到 ,获得积分10
3秒前
wbh发布了新的文献求助10
4秒前
JamesPei应助咚咚咚采纳,获得30
5秒前
小熊熊完成签到,获得积分10
6秒前
Tessa完成签到,获得积分10
6秒前
王心耳完成签到,获得积分10
7秒前
扁舟灬完成签到,获得积分10
7秒前
周婷发布了新的文献求助10
7秒前
7秒前
puff关注了科研通微信公众号
8秒前
8秒前
10秒前
稳重岩完成签到 ,获得积分10
12秒前
loski发布了新的文献求助10
13秒前
步一发布了新的文献求助10
13秒前
14秒前
14秒前
hanleiharry1发布了新的文献求助10
14秒前
14秒前
murry123发布了新的文献求助10
15秒前
痴情的寒云完成签到 ,获得积分10
15秒前
CAOHOU应助张wx_100采纳,获得10
16秒前
17秒前
ppg123应助NightGlow采纳,获得10
18秒前
18秒前
19秒前
emmm发布了新的文献求助10
20秒前
顾矜应助wbh采纳,获得10
21秒前
无辜的夏山完成签到,获得积分10
21秒前
1142722发布了新的文献求助10
22秒前
量子星尘发布了新的文献求助10
23秒前
murry123完成签到,获得积分10
24秒前
齐天大圣关注了科研通微信公众号
25秒前
puff发布了新的文献求助10
26秒前
26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 3989390
求助须知:如何正确求助?哪些是违规求助? 3531487
关于积分的说明 11254109
捐赠科研通 3270153
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809174