Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure
文献类型：期刊论文
| 作者 | Yuan, Ruiwen1,2; Tang, Yongqiang2 ; Wu, Yajing2; Niu, Jinghao2; Zhang, Wensheng2,3
|
| 刊名 | IEEE TRANSACTIONS ON CYBERNETICS
 |
| 出版日期 | 2024-07-10 |
| 页码 | 14 |
| 关键词 | Contrastive learning graph neural network (GNN) graph structure learning (GSL) graph neural network (GNN) graph structure learning (GSL) |
| ISSN号 | 2168-2267 |
| DOI | 10.1109/TCYB.2024.3416621 |
| 通讯作者 | Tang, Yongqiang(yongqiang.tang@ia.ac.cn) ; Zhang, Wensheng(zhangwenshengia@hotmail.com) |
| 英文摘要 | Graph neural networks (GNNs) have achieved considerable success in dealing with graph-structured data by the message-passing mechanism. Actually, this mechanism relies on a fundamental assumption that the graph structure along which information propagates is perfect. However, the real-world graphs are inevitably incomplete or noisy, which violates the assumption, thus resulting in limited performance. Therefore, optimizing graph structure for GNNs is indispensable and important. Although current semi-supervised graph structure learning (GSL) methods have achieved a promising performance, the potential of labels and prior graph structure has not been fully exploited yet. Inspired by this, we examine GSL with dual reinforcement of label and prior structure in this article. Specifically, to enhance label utilization, we first propose to construct the prior label-constrained matrices to refine the graph structure by identifying label consistency. Second, to adequately leverage the prior structure to guide GSL, we develop spectral contrastive learning that extracts global properties embedded in the prior graph structure. Moreover, contrastive fusion with prior spatial structure is further adopted, which promotes the learned structure to integrate local spatial information from the prior graph. To extensively evaluate our proposal, we perform sufficient experiments on seven benchmark datasets, where experimental results confirm the effectiveness of our method and the rationality of the learned structure from various aspects. |
| 资助项目 | National Key Research and Development Program of China[2021ZD0111000] ; National Natural Science Foundation of China[62106266] ; National Natural Science Foundation of China[62206292] ; National Natural Science Foundation of China[U22B2048] ; National Natural Science Foundation of China[62203437] |
| WOS研究方向 | Automation & Control Systems ; Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001271675600001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59248]  |
| 专题 | 精密感知与控制研究中心_人工智能与机器学习 |
| 通讯作者 | Tang, Yongqiang; Zhang, Wensheng |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 3.Guangzhou Univ, Sch Comp Sci & Cyber Engn, Guangzhou 510006, Peoples R China |
| 推荐引用方式 GB/T 7714 | Yuan, Ruiwen,Tang, Yongqiang,Wu, Yajing,et al. Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure[J]. IEEE TRANSACTIONS ON CYBERNETICS,2024:14. |
| APA | Yuan, Ruiwen,Tang, Yongqiang,Wu, Yajing,Niu, Jinghao,&Zhang, Wensheng.(2024).Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure.IEEE TRANSACTIONS ON CYBERNETICS,14. |
| MLA | Yuan, Ruiwen,et al."Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure".IEEE TRANSACTIONS ON CYBERNETICS (2024):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。