中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
HackGAN: Harmonious Cross-Network Mapping Using CycleGAN With Wasserstein-Procrustes Learning for Unsupervised Network Alignment

文献类型：期刊论文

作者Yang, Linyao1,3; Wang, Xiao1,5; Zhang, Jun2; Yang, Jun2; Xu, Yancai1,5; Hou, Jiachen4,5; Xin, Kejun6; Wang, Fei-Yue1,5
刊名IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
出版日期2022-02-02
页码14
关键词Task analysis Optimization Generative adversarial networks Computational modeling Automation Training Standards Embedding generative adversarial network network alignment (NA) optimal transport unsupervised learning
ISSN号2329-924X
DOI10.1109/TCSS.2022.3144350
通讯作者Wang, Xiao(x.wang@ia.ac.cn)
英文摘要Network alignment (NA) that identifies equivalent nodes across networks is an effective tool for integrating knowledge from multiple networks. The state-of-the-art NA methods learn inter-network node similarities based on labeled anchor links, which are costly, time-consuming, and difficult to acquire. Therefore, a few unsupervised network alignment (UNA) methods propose solving NA problems without anchor links. However, most existing UNA methods rely on discriminative attributes to capture nodes' similarities and are hard to obtain optimal one-to-one alignments. Toward these issues, this article proposes a novel method named HackGAN to solve the UNA problem solely based on the structural information. Specifically, HackGAN represents nodes with embeddings based on an unsupervised graph neural network (GNN) to capture their global and local structural features. After that, it initializes mapping functions to transform the embedding spaces of different networks into the same vector space by iteratively solving the Wasserstein-Procrustes problem. The mapping functions are then refined by an adversarial model with cycle-consistency and Sinkhorn distance losses to obtain optimized one-to-one mappings. Based on the distances between mapped embeddings, accurate and robust results are obtained with a collective alignment algorithm. Experimental comparisons on both synthetic and real-world datasets demonstrate the superiority of HackGAN.
WOS关键词PARALLEL CONTROL ; SYSTEMS
资助项目National Key R&D Program of China[2018AAA0101502] ; Science and Technology Project of SGCC (State Grid Corporation of China)
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000751481300001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key R&D Program of China ; Science and Technology Project of SGCC (State Grid Corporation of China)
源URL[http://ir.ia.ac.cn/handle/173211/47376]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者Wang, Xiao
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Wuhan Univ, Sch Elect Engn & Automat, Wuhan 430072, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
4.Macau Univ Sci & Technol, Inst Syst Engn, Taipa 999078, Macao, Peoples R China
5.Qingdao Acad Intelligent Ind, Qingdao 266200, Peoples R China
6.Nanjing Joinmap Data Res Inst, Nanjing 211100, Peoples R China
推荐引用方式
GB/T 7714		 Yang, Linyao,Wang, Xiao,Zhang, Jun,et al. HackGAN: Harmonious Cross-Network Mapping Using CycleGAN With Wasserstein-Procrustes Learning for Unsupervised Network Alignment[J]. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,2022:14.
APA Yang, Linyao.,Wang, Xiao.,Zhang, Jun.,Yang, Jun.,Xu, Yancai.,...&Wang, Fei-Yue.(2022).HackGAN: Harmonious Cross-Network Mapping Using CycleGAN With Wasserstein-Procrustes Learning for Unsupervised Network Alignment.IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,14.
MLA Yang, Linyao,et al."HackGAN: Harmonious Cross-Network Mapping Using CycleGAN With Wasserstein-Procrustes Learning for Unsupervised Network Alignment".IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2022):14.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。