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
UniSKGRep: A unified representation learning framework of social network and knowledge graph

文献类型：期刊论文

作者Shen, Yinghan5,6; Jiang, Xuhui5,6; Li, Zijian5,6; Wang, Yuanzhuo1,4,6; Xu, Chengjin2; Shen, Huawei5,6; Cheng, Xueqi3,5,6
刊名NEURAL NETWORKS
出版日期2023
卷号158页码:142-153
关键词Social knowledge graph Graph representation learning Knowledge graph Social network
ISSN号0893-6080
DOI10.1016/j.neunet.2022.11.010
英文摘要The human-oriented applications aim to exploit behaviors of people, which impose challenges on user modeling of integrating social network (SN) with knowledge graph (KG), and jointly analyzing two types of graph data. However, existing graph representation learning methods merely represent one of two graphs alone, and hence are unable to comprehensively consider features of both SN and KG with profiling the correlation between them, resulting in unsatisfied performance in downstream tasks. Considering the diverse gap of features and the difficulty of associating of the two graph data, we introduce a Unified Social Knowledge Graph Representation learning framework (UniSKGRep), with the goal to leverage the multi-view information inherent in the SN and KG for improving the downstream tasks of user modeling. To the best of our knowledge, we are the first to present a unified representation learning framework for SN and KG. Concretely, the SN and KG are organized as the Social Knowledge Graph (SKG), a unified representation of SN and KG. For the representation learning of SKG, first, two separate encoders in the Intra-graph model capture both the social-view and knowledge-view in two embedding spaces, respectively. Then the Inter-graph model is learned to associate the two separate spaces via bridging the semantics of overlapping node pairs. In addition, the overlapping node enhancement module is designed to effectively align two spaces with the consideration of a relatively small number of overlapping nodes. The two spaces are gradually unified by continuously iterating the joint training procedure. Extensive experiments on two real-world SKG datasets have proved the effectiveness of UniSKGRep in yielding general and substantial performance improvement compared with the strong baselines in various downstream tasks.(c) 2022 Elsevier Ltd. All rights reserved.
资助项目National Natural Science Foundation of China[U1836206] ; National Natural Science Foundation of China[91646120] ; National Natural Science Foundation of China[U21B2046] ; National Natural Science Foundation of China[62172393] ; National Key Research and Development Program of China[2018YFB1402601] ; Zhongyuanyingcai program[204200510002] ; Major Public Welfare Project of Henan Province[201300311200]
WOS研究方向Computer Science ; Neurosciences & Neurology
语种英语
WOS记录号WOS:000892217500012
出版者PERGAMON-ELSEVIER SCIENCE LTD
源URL[http://119.78.100.204/handle/2XEOYT63/20226]  
专题中国科学院计算技术研究所期刊论文
通讯作者Wang, Yuanzhuo
作者单位1.6 Kexueyuan South Rd Zhongguancun, Beijing 100190, Peoples R China
2.Int Digital Econ Acad, Shenzhen, Guangdong, Peoples R China
3.Inst Comp Technol, Chinese Acad Sci, Key Lab Network data & Sci & Technol, Beijing, Peoples R China
4.Zhongke Big Data Acad, Zhengzhou, Henan, Peoples R China
5.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing, Peoples R China
6.Chinese Acad Sci, Inst Comp Technol, Data Intelligent Syst Res Ctr, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Shen, Yinghan,Jiang, Xuhui,Li, Zijian,et al. UniSKGRep: A unified representation learning framework of social network and knowledge graph[J]. NEURAL NETWORKS,2023,158:142-153.
APA Shen, Yinghan.,Jiang, Xuhui.,Li, Zijian.,Wang, Yuanzhuo.,Xu, Chengjin.,...&Cheng, Xueqi.(2023).UniSKGRep: A unified representation learning framework of social network and knowledge graph.NEURAL NETWORKS,158,142-153.
MLA Shen, Yinghan,et al."UniSKGRep: A unified representation learning framework of social network and knowledge graph".NEURAL NETWORKS 158(2023):142-153.

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。