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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
HIRE: Distilling high-order relational knowledge from heterogeneous graph neural networks

文献类型：期刊论文

作者Liu, Jing2,3; Zheng, Tongya1; Hao, Qinfen3
刊名NEUROCOMPUTING
出版日期2022-10-01
卷号507页码:67-83
关键词Graph embedding Heterogeneous graph Graph neural networks Knowledge distillation
ISSN号0925-2312
DOI10.1016/j.neucom.2022.08.022
英文摘要Researchers have recently proposed plenty of heterogeneous graph neural networks (HGNNs) due to the ubiquity of heterogeneous graphs in both academic and industrial areas. Instead of pursuing a more powerful HGNN model, in this paper, we are interested in devising a versatile plug-and-play module, which accounts for distilling relational knowledge from pre-trained HGNNs. To the best of our knowledge, we are the first to propose a HIgh-order RElational (HIRE) knowledge distillation framework on heterogeneous graphs, which can significantly boost the prediction performance regardless of model architectures of HGNNs. Concretely, our HIRE framework initially performs first-order node-level knowledge distillation, which encodes the semantics of the teacher HGNN with its prediction logits. Meanwhile, the second-order relation-level knowledge distillation imitates the relational correlation between node embeddings of different types generated by the teacher HGNN. Extensive experiments on various popular HGNNs models and three real-world heterogeneous graphs demonstrate that our method obtains consistent and considerable performance enhancement, proving its effectiveness and generalization ability. (c) 2022 Elsevier B.V. All rights reserved.
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000911757100006
出版者ELSEVIER
源URL[http://119.78.100.204/handle/2XEOYT63/20013]  
专题中国科学院计算技术研究所期刊论文
通讯作者Hao, Qinfen
作者单位1.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, SKLP, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Jing,Zheng, Tongya,Hao, Qinfen. HIRE: Distilling high-order relational knowledge from heterogeneous graph neural networks[J]. NEUROCOMPUTING,2022,507:67-83.
APA Liu, Jing,Zheng, Tongya,&Hao, Qinfen.(2022).HIRE: Distilling high-order relational knowledge from heterogeneous graph neural networks.NEUROCOMPUTING,507,67-83.
MLA Liu, Jing,et al."HIRE: Distilling high-order relational knowledge from heterogeneous graph neural networks".NEUROCOMPUTING 507(2022):67-83.

入库方式： OAI收割

来源：计算技术研究所

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。