Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining

doi:10.1145/3608480

	Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining
	Zhu, Yanqiao1 ; Xu, Yichen 2; Yu, Feng3 ; Liu, Qiang4,5 ; Wu, Shu4,5
发表期刊	ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
ISSN	2157-6904
	2023-10-01
卷号	14 期号:5 页码:21
通讯作者	Wu, Shu(shu.wu@nlpr.ia.ac.cn)
摘要	Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous Graph Neural Networks (GNN) require a large number of labeled nodes, which may not be accessible in real-world applications. To this end, we present a novel unsupervised graph neural network model with Cluster-aware Self-training and Refining (CLEAR). Specifically, in the proposed CLEAR model, we perform clustering on the node embeddings and update the model parameters by predicting the cluster assignments. To avoid degenerate solutions of clustering, we formulate the graph clustering problem as an optimal transport problem and leverage a balanced clustering strategy. Moreover, we observe that graphs often contain inter-class edges, which mislead the GNN model to aggregate noisy information from neighborhood nodes. Therefore, we propose to refine the graph topology by strengthening intra-class edges and reducing node connections between different classes based on cluster labels, which better preserves cluster structures in the embedding space. We conduct comprehensive experiments on two benchmark tasks using real-world datasets. The results demonstrate the superior performance of the proposed model over baseline methods. Notably, our model gains over 7% improvements in terms of accuracy on node clustering over state-of-the-arts.
关键词	Cluster-aware self-training and refining unsupervised learning graph representation learning
DOI	10.1145/3608480
关键词[WOS]	NEURAL-NETWORKS
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62141608] ; National Natural Science Foundation of China[U19B2038] ; National Natural Science Foundation of China[62206291]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems
WOS记录号	WOS:001087277500006
出版者	ASSOC COMPUTING MACHINERY
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/54383
专题	多模态人工智能系统全国重点实验室智能感知与计算研究中心
通讯作者	Wu, Shu
作者单位	1.Univ Calif Los Angeles, 3551 Boelter Hall,580 Portola Plaza, Los Angeles, CA 90095 USA 2.Ecole Polytech Fed Lausanne, CH-1015 Lausanne, Switzerland 3.DP Technol, 2 Haidian East 3rd St, Beijing 100080, Peoples R China 4.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhu, Yanqiao,Xu, Yichen,Yu, Feng,et al. Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining[J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY,2023,14(5):21.
APA	Zhu, Yanqiao,Xu, Yichen,Yu, Feng,Liu, Qiang,&Wu, Shu.(2023).Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining.ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY,14(5),21.
MLA	Zhu, Yanqiao,et al."Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining".ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 14.5(2023):21.