Please wait a minute...
Data Analysis and Knowledge Discovery  2023, Vol. 7 Issue (6): 15-25    DOI: 10.11925/infotech.2096-3467.2022.0361
Current Issue | Archive | Adv Search |
Technology Recognition and Link Prediction Method Based on GNN
Xu Xin(),Li Qian,Yao Zhanlei
Faculy of Economics and Management, East China Normal University, Shanghai 200062, China
Download: PDF (1064 KB)   HTML ( 31 ) 
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper integrates time features into a patent IPC co-occurrence network and trains the GNN model for link prediction. It aims to provide a reference for technology discovery and knowledge supply. [Methods] First, we collected the patent data on “privacy protection” to construct an IPC co-occurrence network. Then, we assigned time distribution, stability, and attention features to the network nodes. Third, we trained the GraphSAGE model to obtain the IPC nodes’ representation and predict the link score between them. It provides assistance and support for technology opportunity mining. [Results] Compared with the traditional link prediction method based on node similarity and the Node2Vec, the proposed model achieved a 30% improvement in the AUC metric. [Limitations] As a deep learning model, GNN has some disadvantages in training time. [Conclusions] Our new link prediction method exhibits high prediction accuracy. Combined with the time characteristics, it can capture the dynamic characteristics of nodes and provide valuable insights for technology discovery and other tasks.
Key words： Link Prediction      Graph Neural Network      Time Features      Technology Discovery     
Received: 18 April 2022      Published: 09 August 2023
ZTFLH:  G35  
Fund:Soft Science Research Projects of Science and Technology Innovation Action Plan Shanghai 2021(21692195900)
Corresponding Authors: Xu Xin，ORCID：0000-0001-7020-3135，E-mail： xxu@infor.ecnu.edu.cn。   
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Xin Xu
Qian Li
Zhanlei Yao

Cite this article:

Xu Xin, Li Qian, Yao Zhanlei. Technology Recognition and Link Prediction Method Based on GNN. Data Analysis and Knowledge Discovery, 2023, 7(6): 15-25.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2022.0361     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2023/V7/I6/15

专利IPC共现网络 值
节点数 4 595
边数 45 436
平均聚集系数 0.683 5
Basic Attributes of Dataset
Influence of Model Parameters
Comparison Results of Baseline Model
方法

训练集比例		 60% 65% 70% 75% 80% 85% 90%
AA 0.670 7 0.681 5 0.657 4 0.717 7 0.658 7 0.746 0 0.690 5
CN 0.673 7 0.684 9 0.588 0 0.703 3 0.622 8 0.616 0 0.595 2
Jaccard 0.681 7 0.694 2 0.624 0 0.711 5 0.694 6 0.656 0 0.726 2
PA 0.658 7 0.650 7 0.645 4 0.665 1 0.664 7 0.698 4 0.595 2
RA 0.661 7 0.654 1 0.664 0 0.612 4 0.712 6 0.616 0 0.642 9
Node2Vec 0.834 6 0.824 9 0.823 8 0.826 4 0.841 4 0.833 0 0.838 2
GraphSAGE_T 0.950 1 0.960 2 0.947 9 0.951 8 0.953 4 0.955 3 0.940 4
AUC of Link Prediction Experiments
Time-Consuming Influence of Training Set Proportion-Baseline
Time-Consuming Influence of Training Set Proportion-GraphSAGE_T
Model 年份
分布
特征		 时间
关注度
特征		 时间
稳定性
特征		 AUC
GraphSAGE_T_V1 √ √ × 0.936 1
GraphSAGE_T_V2 √ × √ 0.931 5
GraphSAGE_T_V3 × √ √ 0.920 9
GraphSAGE_T_V4 × × × 0.884 1
GraphSAGE_T √ √ √ 0.960 2
Influence of Time Characteristics
Prediction Effect of Enhanced Links
IPC组合 链接分数
<G06F21/62， G06F21/60> 0.817 1
<G06F21/62， H04L29/06> 0.776 1
<G06F21/62， G06F21/64> 0.712 1
<G06F21/62， G06K9/62> 0.711 9
<G06F21/62， H04L29/08> 0.705 2
<G06F21/62， G06N3/08> 0.700 6
<G06F21/62， G06F21/32> 0.696 5
<G06F21/62， G06N3/04> 0.692 6
<G06F21/62， G06Q40/04> 0.682 5
<G06F21/62， G06F17/30> 0.674 9
<G06F21/62， G06Q20/38> 0.674 2
<G06F21/62， H04L9/08> 0.670 5
<G06F21/62， H04L9/32> 0.665 5
<G06F21/62， G06K9/00> 0.658 9
<G06F21/62， H04L9/00> 0.652 6
Enhanced Links of G06F21/62
Prediction Effect of New Links
IPC组合 链接分数
<G06F21/62， G11B11/00> 0.865 7
<G06F21/62， G02B27/00> 0.835 7
<G06F21/62， G06T5/40> 0.806 3
<G06F21/62， G11B27/10> 0.762 5
<G06F21/62， G06F8/71> 0.751 5
<G06F21/62， G06F7/72> 0.731 4
<G06F21/62， G06F12/06> 0.729 5
<G06F21/62， B65F1/06> 0.717 3
<G06F21/62， G06T1/20> 0.702 1
<G06F21/62， A47B37/00> 0.694 6
<G06F21/62， G06T5/10> 0.691 4
<G06F21/62， G06F11/10> 0.689 5
<G06F21/62， A47C1/00> 0.687 6
<G06F21/62， A47B13/00> 0.685 0
<G06F21/62， G06F21/54> 0.681 7
New Links of G06F21/62
Prediction Effect of Declining Links
IPC组合 链接分数
<G06F21/62， G08B25/08> 0.145 7
<G06F21/62， G08B25/00> 0.179 6
<G06F21/62， H04W4/02> 0.216 8
<G06F21/62， H04L12/28> 0.235 5
<G06F21/62， H04W8/24> 0.252 6
<G06F21/62， H04W4/14> 0.255 4
<G06F21/62， H04N5/232> 0.272 1
<G06F21/62， H04M1/57> 0.272 1
Declining Links of G06F21/62
[1] 徐燕. 基于数据挖掘的网络链接预测研究[J]. 信息网络安全, 2017(6): 30-34.
[1] (Xu Yan. Research on Network Link Prediction Based on Data Mining[J]. Netinfo Security, 2017(6): 30-34.)
[2] Nassar H, Benson A R, Gleich D F. Pairwise Link Prediction[OL]. arXiv Preprint, arXiv: 1907.04503.
[3] 蔡彪, 李蕊岑, 吴媛媛. 相似性特征对链路预测的影响与增强[J]. 计算机应用, 2021, 41(9): 2569-2577.
doi: 10.11772/j.issn.1001-9081.2020111744
[3] (Cai Biao, Li Ruicen, Wu Yuanyuan. Impact and Enhancement of Similarity Features on Link Prediction[J]. Journal of Computer Applications, 2021, 41(9): 2569-2577.)
doi: 10.11772/j.issn.1001-9081.2020111744
[4] 宫雪, 崔雷. 基于医学主题词共现网络的链接预测研究[J]. 情报杂志, 2018, 37(1): 66-71.
[4] (Gong Xue, Cui Lei. Link Prediction in MeSH Terms Co-Occurring Networks[J]. Journal of Intelligence, 2018, 37(1): 66-71.)
[5] Nguyen-Thi A T, Nguyen P Q, Ngo T D, et al. Transfer AdaBoost SVM for Link Prediction in Newly Signed Social Networks Using Explicit and PNR Features[J]. Procedia Computer Science, 2015, 60: 332-341.
doi: 10.1016/j.procs.2015.08.135
[6] Hasan M A, Chaoji V, Salem S, et al. Link Prediction Using Supervised Learning[C]// Proceedings of the SDM’06 Workshop on Link Analysis, Counter-Terrorism and Security. 2006.
[7] Ou M D, Cui P, Pei J, et al. Asymmetric Transitivity Preserving Graph Embedding[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 1105-1114.
[8] Perozzi B, Al-Rfou R, Skiena S. DeepWalk: Online Learning of Social Representations[C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2014: 701-710.
[9] Grover A, Leskovec J. Node2vec: Scalable Feature Learning for Networks[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 855-864.
[10] Bruna J, Zaremba W, Szlam A, et al. Spectral Networks and Locally Connected Networks on Graphs[OL]. arXiv Preprint, arXiv: 1312.6203.
[11] Kipf T N, Welling M. Semi-Supervised Classification with Graph Convolutional Networks[OL]. arXiv Preprint, arXiv: 1609.02907.
[12] Hamilton W L, Ying R, Leskovec J. Inductive Representation Learning on Large Graphs[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 1025-1035.
[13] Velickovic P, Cucurull G, Casanova A, et al. Graph Attention Networks[C]// Proceedings of the 6th International Conference on Learning Representations. 2018.
[14] 王慧, 乐孜纯, 龚轩, 等. 基于特征学习的链路预测模型TNTlink[J]. 计算机科学, 2020, 47(12): 245-251.
doi: 10.11896/jsjkx.190700020
[14] (Wang Hui, Le Zichun, Gong Xuan, et al. TNTlink Prediction Model Based on Feature Learning[J]. Computer Science, 2020, 47(12): 245-251.)
doi: 10.11896/jsjkx.190700020
[15] Chakraborty R, Das R, Chakraborty N. Link Prediction in Signed Networks[C]// Proceedings of the 31st ACM Conference on Hypertext and Social Media. New York: ACM, 2020: 235-236.
[16] 张艳红, 王宝会. 基于深度神经网络的社会媒体网络分析[J]. 计算机科学, 2016, 43(4): 252-255.
doi: 10.11896/j.issn.1002-137X.2016.04.051
[16] (Zhang Yanhong, Wang Baohui. Analysis of Social Media Networks Based on Deep Neural Networks[J]. Computer Science, 2016, 43(4): 252-255.)
doi: 10.11896/j.issn.1002-137X.2016.04.051
[17] 刘思, 刘海, 陈启买, 等. 基于网络表示学习与随机游走的链路预测算法[J]. 计算机应用, 2017, 37(8): 2234-2239.
doi: 10.11772/j.issn.1001-9081.2017.08.2234
[17] (Liu Si, Liu Hai, Chen Qimai, et al. Link Prediction Algorithm Based on Network Representation Learning and Random Walk[J]. Journal of Computer Applications, 2017, 37(8): 2234-2239.)
doi: 10.11772/j.issn.1001-9081.2017.08.2234
[18] Wang Z T, Lei Y, Li W J. Neighborhood Interaction Attention Network for Link Prediction[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 2019: 2153-2156.
[19] 柴庆凤, 翟东升, 蔡力伟, 等. 基于专利网络链接模型的技术链接机会预测方法研究[J]. 情报理论与实践, 2020, 43(12): 111-119.
doi: 10.16353/j.cnki.1000-7490.2020.12.017
[19] (Chai Qingfeng, Zhai Dongsheng, Cai Liwei, et al. Study on the Method of the Technology Link Opportunity Forecasting Based on Patent Network Link Model[J]. Information Studies :Theory & Application, 2020, 43(12): 111-119.)
doi: 10.16353/j.cnki.1000-7490.2020.12.017
[20] Fındık O, Özkaynak E. Link Prediction Based on Node Weighting in Complex Networks[J]. Soft Computing, 2021, 25(3): 2467-2482.
doi: 10.1007/s00500-020-05314-8
[21] Mishra S, Singh S, Biswas B. MNERLP-MUL: Merged Node and Edge Relevance Based Link Prediction in Multiplex Networks[J]. Journal of Computational Science, 2022, 60(3): 101606.
doi: 10.1016/j.jocs.2022.101606
[22] Ren H X, Kokai G F, Turner W J, et al. ParaGraph: Layout Parasitics and Device Parameter Prediction Using Graph Neural Networks[C]// Proceedings of the 57th ACM/EDAC/IEEE Design Automation Conference. New York: ACM, 2020: 1-6.
[23] 张欣环, 刘宏杰, 施俊庆, 等. 基于时空特征向量的长短期记忆人工神经网络的城市公交旅行时间预测[J]. 计算机应用, 2021, 41(3): 875-880.
doi: 10.11772/j.issn.1001-9081.2020060467
[23] (Zhang Xinhuan, Liu Hongjie, Shi Junqing, et al. LSTM and Artificial Neural Network for Urban Bus Travel Time Prediction Based on Spatiotemporal Eigenvectors[J]. Journal of Computer Applications, 2021, 41(3): 875-880.)
doi: 10.11772/j.issn.1001-9081.2020060467
[24] 李倩, 陈红伶, 许鑫. 基于时间加权A-T模型的学者相似度计算研究[J]. 情报杂志, 2021, 40(9): 170-177.
[24] (Li Qian, Chen Hongling, Xu Xin. Research on Scholars Similarity Calculation Based on Time Weighted A-T Model[J]. Journal of Intelligence, 2021, 40(9): 170-177.)
[25] Anderson J R. Learning and Memory: An Integrated Approach[M]. Wiley, 1999.
[26] 江志恒, 刘乃芩. 论遗忘函数——关于记忆心理学的数学讨论[J]. 心理学动态, 1988(3): 56-60.
[26] (Jiang Zhiheng, Liu Naiqin. On Forgetting Function—A Mathematical Discussion on Memory Psychology[J]. Advances in Psychological Science, 1988(3): 56-60.)
[27] 国际专利分类[EB/OL]. [2022-02-21]. https://www.wipo.int/classifications/ipc/zh/.
[27] (International Patent Classification[EB/OL]. [2022-02-21]. https://www.wipo.int/classifications/ipc/zh/.)
[28] 关于国际专类分类[EB/OL]. [2022-02-21]. https://www.wipo.int/classifications/ipc/zh/preface.html.
[28] (About the International Patent Classification[EB/OL]. [2022-02-21]. https://www.wipo.int/classifications/ipc/zh/preface.html.)
[1] Pei Wei, Sun Shuifa, Li Xiaolong, Lu Ji, Yang Liu, Wu Yirong. Medical Named Entity Recognition with Domain Knowledge[J]. 数据分析与知识发现, 2023, 7(3): 142-154.
[2] Cheng Quan, She Dexin. Drug Recommendation Based on Graph Neural Network with Patient Signs and Medication Data[J]. 数据分析与知识发现, 2022, 6(9): 113-124.
[3] Liu Kan, Xu Qinya, Yu Lu. Constructing Knowledge Graph for Business Environment[J]. 数据分析与知识发现, 2022, 6(4): 82-96.
[4] Wang Lu, Le Xiaoqiu. Identifying Topic-Problem Instances Based on Syntactic Dependency Enhancement[J]. 数据分析与知识发现, 2022, 6(12): 13-22.
[5] Wang Jie,Gao Yuan,Zhang Lei,Ma Liwen,Feng Jun. Predicting Short-Term Urban Traffics Based on Causality Analysis Graph[J]. 数据分析与知识发现, 2022, 6(11): 111-125.
[6] Gu Yaowen,Zheng Si,Yang Fengchun,Li Jiao. GNN-MTB: An Anti-Mycobacterium Drug Virtual Screening Model Based on Graph Neural Network[J]. 数据分析与知识发现, 2022, 6(11): 93-102.
[7] Feng Xiaodong, Hui Kangxin. Topic Clustering for Social Media Texts with Heterogeneous Graph Neural Networks[J]. 数据分析与知识发现, 2022, 6(10): 9-19.
[8] Huang Xuejian, Liu Yuyang, Ma Tinghuai. Classification Model for Scholarly Articles Based on Improved Graph Neural Network[J]. 数据分析与知识发现, 2022, 6(10): 93-102.
[9] Shan Xiaohong,Wang Chunwen,Liu Xiaoyan,Han Shengxi,Yang Juan. Identifying Lead Users in Open Innovation Community from Knowledge-based Perspectives[J]. 数据分析与知识发现, 2021, 5(9): 85-96.
[10] Gu Yaowen, Zhang Bowen, Zheng Si, Yang Fengchun, Li Jiao. Predicting Drug ADMET Properties Based on Graph Attention Network[J]. 数据分析与知识发现, 2021, 5(8): 76-85.
[11] Wu Shengnan, Tian Ruonan, Pu Hongjun, Liang Wenqi, Zhang Yafei, Yu Qi, He Peifeng. Predicting Related Medical Topics from Social Media[J]. 数据分析与知识发现, 2021, 5(12): 98-109.
[12] Wu Shengnan, Pu Hongjun, Tian Ruonan, Liang Wenqi, Yu Qi. Network Structure’s Impacts on Link Prediction Algorithm from Meta-Analysis Perspective[J]. 数据分析与知识发现, 2021, 5(11): 102-113.
[13] Yu Chuanming, Zhang Zhengang, Kong Lingge. Comparing Knowledge Graph Representation Models for Link Prediction[J]. 数据分析与知识发现, 2021, 5(11): 29-44.
[14] Chen Wenjie. Predicting Research Collaboration Based on Translation Model[J]. 数据分析与知识发现, 2020, 4(10): 28-36.
[15] Chuanming Yu,Haonan Li,Manyi Wang,Tingting Huang,Lu An. Knowledge Representation Based on Deep Learning:Network Perspective[J]. 数据分析与知识发现, 2020, 4(1): 63-75.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626，82624938   E-mail:jishu@mail.las.ac.cn