基于图卷积网络的多源本体相似度计算方法

doi:10.11959/j.issn.2096-109x.2021071

Abstract

Abstract:

In the information age, the amount of data is growing exponentially.However, different data sources are heterogeneous, which makes it inconvenient to share and multiplex data.With the rapid development of semantic network, ontology mapping is an effective method to solve this problem.The core of ontology mapping is ontology similarity calculation.Therefore, a calculation method based on graph convolution network was proposed.Firstly, ontologiesare modeled as a heterogeneous graph network, then the graph convolution network was used to learn the text embedding rules, which made ontologies were definedin global unified representation.Lastly, multisource data fusion was completed.The experimental results show that the accuracy of the proposed method is higher than other methods, and the accuracy of multi-source data fusion was effectively improved.

Key words: heterogeneous data fusion, graph convolution network, ontology mapping, similarity calculation

CLC Number:

TP393

Liuqian SUN, Yuliang WEI, Bailing WANG. Novel similarity calculation method of multisource ontology based on graph convolution network[J]. Chinese Journal of Network and Information Security, 2021, 7(5): 149-155.

Figures/Tables 8

References 18

[1]	杨泉 . 基于遗传算法的词语语义相似度计算研究[J]. 计算机技术与发展, 2021,31(2): 8-13.
	YANG Q . Research on word semantic similarity calculation based on genetic algorithm[J]. Computer Technology and Development, 2021,31(2): 8-13.
[2]	丁悦航, 于洪涛, 黄瑞阳, 李英乐 . 本体摘要技术综述[J]. 网络与信息安全学报, 2018,4(10): 12-21.
	DING Y H. , YU H T , HUANG R Y . Ontology summarization technology survey[J]. Chinese Journal of Network and Information Security, 2018,4(10): 12-21.
[3]	DAO W . Distance learning techniques for ontology similarity measuring and ontology mapping[J]. Cluster Computing, 2017,20(2): 959-968.
[4]	周爱武, 翟增辉, 刘慧婷 . 基于模拟退火算法改进的 BP 神经网络算法[J]. 微电子学与计算机, 2016,33(4): 144-147.
	ZHOU A W , ZHAI Z H , LIU H T ,et al. Improved BP neural network based on simulated annealing[J]. Mi-croelectronics and Computer, 2016,33(4): 144-147.
[5]	RADA R , MILI H , BICKNELL E . Development and application of a metric on semantic nets[J]. IEEE,Transactions on Systems,Man and Cybernetics, 1989,19( 1): 17-30.
[6]	孙丽莉, 张小刚 . 基于 WordNet 的概念语义相似度的计算方法[J]. 统计与决策, 2017(23): 79-82.
	SUN L L , ZHANG X G . A novel concept semantic similarity calculation method based on WordNet[J]. Statistics ＆ Decision, 2017(23): 79-82.
[7]	TVERSKY A . Feature of similarity[J]. Psychological Review, 1997,84(4): 222-226.
[8]	郑志蕴, 阮春阳, 李伦 ,等. 本体语义相似度自适应综合加权算法研究[J]. 计算机科学, 2016,43(10): 242-247.
	ZHENG Z Y , RUAN C Y , LI L ,et al. Adaptive ontology semantic similarity comprehensive weighted algorithm[J]. Computer Science, 2016,43(10): 242-247.
[9]	卢家伟, 薛醒思, 肖祖宇 ,等. 一种基于混合语义相似度度量方法的本体元匹配技术[J]. 宝鸡文理学院学报(自然科学版), 2020,40(2): 59-63.
	LU J W , XUE X S , XIAO Z G ,et al. An ontology meta-matching technique based on the hybrid semantic similarity measure[J]. Journal of Baoji University of Arts and Sciences(Natural Science Edition), 2020,40(2): 242-247.
[10]	郭小华, 彭琦, 邓涵 ,等. 基于边权重的WordNet词语相似度计算[J]. 计算机工程与应用, 2018,54(1): 172-178.
	GUO X H , PENG Q , DENG H ,et al. Edge weight-based word similarity computation in WordNet[J]. Computer Engineering and Applications, 2018,54(1): 172-178.
[11]	LI Y , GAO D Q . Research on entity similarity computationin knowledge map[J]. Chinese Journal of Information Science, 2017,31(1): 145-151.
[12]	许飞翔, 叶霞, 李琳琳 ,等. 基于SA-BP算法的本体概念语义相似度综合计算[J]. 计算机科学, 2020,47(1): 199-204.
	XU F X , YE X , LI L L ,et al. Comprehensive calculation of semantic similarity of ontology concept based on SA-BP[J]. Computer Science, 2020,47(1): 199-204.
[13]	曲强, 于洪涛, 黄瑞阳 . 基于图卷积网络的社交网络 Spammer检测技术[J]. 网络与信息安全学报, 2018,4(5): 39-46.
	QU Q YU H T , HUANG R Y . Spammer detection technology of social network based on graph convolution network[J]. Chinese Journal of Network and Information Security, 2018,4(5): 39-46.
[14]	PENG H , LI J . Large-scale hierarchical text classification with recursively regularized deep graph[J]. International World Wide Web Conference, 2018: 1063-1072.
[15]	ROUSSEAU F , KIAGIAS E . Text categorization as a graph classification problem[J]. ACL, 2015,1: 1702-1712.
[16]	KIPF T N . Semi-supervised classification with graph convolutional networks[J]. ICLR, 2017.
[17]	姚佳奇, 徐正国, 燕继坤 ,等. GCN-PU：基于图卷积网络的PU文本分类算法[J]. 计算机工程与应用, 2020: 1-8.
	YAO J Q.XU Z G , YE J K ,et al. GCN-PU text classification algorithm based on graph convolutional network[J]. Computer Engineering and Applications. 2020: 1-8.
[18]	李慧, 胡吉霞 . 一种基于图卷积自编码模型的多维度学科知识网络融合方法[J]. 图书情报工作, 2020,64(18): 114-125.
	LI H , HU J X . Multi-dimensional subject knowledge network fusion method based on graph convolution self-encoding model[J]. Library and Information Service, 2020,64(18): 114-125.

Metrics

Recommended 0

No Suggested Reading articles found!

方法	优点	缺点
基于语义距离的相似度计算方法	计算复杂度较低	考虑因素单一，使结果准确性不高且不稳定
基于信息内容的相似度计算方法	结果较准确	针对完备性不高的语料库，算法不具备鲁棒性
基于概念属性的相似度计算方法	结果较准确	针对不同本体，算法不具备普适性
混合式语义相似度计算方法	结果较客观准确	计算复杂度高
基于深度学习的相似度计算方法	结果准确	收敛性差

计算相似度方法	代表性文献	第一组	第二组	第三组	第四组	第五组	第六组
人工评价	—	0.735 5	0.596 7	0.638 6	0.266 1	0.128 3	0.908 9
基于语义距离的相似度计算方法	文献[5]	0.547 8	0.671 2	0.601 9	0.362 1	0.562 4	0.928 7
基于信息内容的相似度计算方法	文献[6]	0.991 2	0.172 2	0.351 3	0.266 1	0.133 9	0.987 2
基于概念属性的相似度计算方法	文献[7]	0.802 8	0.821 1	0.211 2	0.503 2	0.003 7	0.740 3
混合式语义相似度计算方法	文献[8,9]	0.357 2	0.308 8	0.708 9	0.100 2	0.067 1	0.653 2
基于SA-BP算法的相似度计算方法	文献[12]	0.498 4	0.201 9	0.339 8	0.099 8	0.089 2	0.798 7
基于GCN的相似度计算方法	—	0.692 1	0.387 1	0.511 4	0.112 7	0.138 2	0.887 3

计算相似度方法	误差最大值	误差平均值	标准差	皮尔逊相关系数
基于语义距离的相似度计算方法	0.434 1	0.141 4	0.141 5	0.715 6
基于信息内容的相似度计算方法	0.424 5	0.175 2	0.158 1	0.781 5
基于概念属性的相似度计算方法	0.427 4	0.208 2	0.113 7	0.680 0
混合式语义相似度计算方法	0.378 3	0.203 2	0.115 3	0.834 9
基于SA-BP算法的相似度计算方法	0.394 8	0.198 8	0.123 0	0.898 3
基于GCN的相似度计算方法	0.209 7	0.094 2	0.074 0	0.960 2

Novel similarity calculation method of multisource ontology based on graph convolution network

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 18

Related Articles 15

Metrics

Recommended 0

[1]	Xianyi CHEN, Jun GU, Kai YAN, Dong JIANG, Linfeng XU, Zhangjie FU. Double adversarial attack against license plate recognition system [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 16-27.
[2]	Tianpeng YE, Xiang LIN, Jianhua LI, Xuankai ZHANG, Liwen XU. Personalized lightweight distributed network intrusion detection system in fog computing [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 28-37.
[3]	Lijun ZU, Yalin CAO, Xiaohua MEN, Zhihui LYU, Jiawei YE, Hongyi LI, Liang ZHANG. Adaptive selection method of desensitization algorithm based on privacy risk assessment [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 49-59.
[4]	Ruiqi XIA, Manman LI, Shaozhen CHEN. Identification on the structures of block ciphers using machine learning [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 79-89.
[5]	Jingyi YUAN, Zichuan LI, Guojun PENG. EN-Bypass: a security assessment method on e-mail user interface notification [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 90-101.
[6]	Feng YU, Qingxin LIN, Hui LIN, Xiaoding WANG. Privacy-enhanced federated learning scheme based on generative adversarial networks [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 113-122.
[7]	Chuntao ZHU, Chengxi YIN, Bolin ZHANG, Qilin YIN, Wei LU. Forgery face detection method based on multi-domain temporal features mining [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 123-134.
[8]	Xiaomeng LI, Daidou GUO, Xunfang ZHUO, Heng YAO, Chuan QIN. Carrier-independent screen-shooting resistant watermarking based on information overlay superimposition [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 135-149.
[9]	Zhao CAI, Tao JING, Shuang REN. Survey on Ethereum phishing detection technology [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 21-32.
[10]	Yan PAN, Wei LIN, Yuefei ZHU. Progressive active inference method of protocol state machine [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 81-93.
[11]	Pan YANG, Fei KANG, Hui SHU, Yuyao HUANG, Xiaoshao LYU. Binary program taint analysis optimization method based on function summary [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 115-131.
[12]	Tian XIAO, Zhihao JIANG, Peng TANG, Zheng HUANG, Jie GUO, Weidong QIU. High-performance directional fuzzing scheme based on deep reinforcement learning [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 132-142.
[13]	Chenghao YUAN, Yong LI, Shuang REN. Dynamic multi-keyword searchable encryption scheme [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 143-153.
[14]	Zezhou HOU, Jiongjiong REN, Shaozhen CHEN. Security evaluation for parameters of SIMON-like cipher based on neural network distinguisher [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 154-163.
[15]	Xuejing GUO, Yixiang FANG, Yi ZHAO, Tianzhu ZHANG, Wenchao ZENG, Junxiang WANG. Traditional guidance mechanism based deep robust watermarking [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 175-183.