[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.
许鑫, 李倩, 姚占雷. 基于图神经网络的技术识别链接预测方法研究*[J]. 数据分析与知识发现, 2023, 7(6): 15-25.
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.
(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
(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.
(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.
(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
(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.
(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.
(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
(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.
(Jiang Zhiheng, Liu Naiqin. On Forgetting Function—A Mathematical Discussion on Memory Psychology[J]. Advances in Psychological Science, 1988(3): 56-60.)