|
|
|
| Scientific Collaboration Recommendation Based on Network Embedding |
| Yu Chuanming1, Lin Aochen1, Zhong Yunci1, An Lu2 |
1.School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan 430073
2.School of Information, Wuhan University, Wuhan 430072 |
|
|
|
|
Abstract This paper researched a scientific collaboration recommendation model in the financial field based on network embedding to promote the formation of a research team in the same research field and improve the efficiency of research. The model integrates two types of network embedding models; one of these is based on the location of vertices, while the other is integrated with network structure. A binary operator for the representation of two vertices was employed to generate a representation of edge. Combining network embedding and machine learning, the model trained a logic regression classifier with the representation of edges as features, and the labels acquired from the classifier were the results of link prediction. By analyzing papers in the financial and physical research fields, several scientific collaboration networks were constructed. The experiments confirm that the proposed integrated model has achieved better performance than single models on the value of AUC, with the efficiency improved by up to 2%; even on a small training set, the value of AUC still reached 60%. The proposed model proved to be feasible in scientific collaboration recommendation, which will effectively promote the formation of a research team in the same field.
|
|
Received: 08 November 2018
|
|
|
|
1 PerozziB, Al-RfouR, SkienaS. DeepWalk: Online learning of social representations[C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2014: 701-710.
2 GroverA, LeskovecJ. Node2vec: Scalable feature learning for networks[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2016: 855-864.
3 TangJ, QuM, WangM Z, et al. LINE: Large-scale information network embedding[C]// Proceedings of the 24th International Conference on World Wide Web. Switzerland: International World Wide Web Conferences Steering Committee, 2015: 1067-1077.
4 WangD X, CuiP, ZhuW W. Structural deep network embedding[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2016: 1225-1234.
5 Liben-NowellD, KleinbergJ. The link-prediction problem for social networks[J]. Journal of the American Society for Information Science and Technology, 2007, 58(7): 1019-1031.
6 ChenJ, GeyerW, DuganC, et al. Make new friends, but keep the old: Recommending people on social networking sites[C]// Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2009: 201-210.
7 AdamicL, AdarE. How to search a social network[J]. Social Networks, 2005, 27(3): 187-203.
8 TanP N, SteinbachM, KumarV. Introduction to data mining[M]. Boston: Addison Wesley, 2005: 65-84.
9 CostaL F, RodriguesF A, TraviesoG, et al. Characterization of complex networks: A survey of measurements[J]. Advances in Physics, 2007, 56(1): 167-242.
10 KatzL. A new status index derived from scientometric analysis[J]. Psychometrika, 1953, 18(1): 39-43.
11 PapadimitriouA, SymeonidisP, ManolopoulosY. Fast and accurate link prediction in social networking systems[J]. Journal of Systems and Software, 2012, 8(5): 2119-2132.
12 PanJ, YangH, FaloutsosC, et al. Automatic multimedia cross-modal correlation discovery[C]// Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Ming. New York: ACM Press, 2004: 653-658.
13 YanE, GunsR. Predicting and recommending collaborations: An author-, institution-, and country-level analysis[J]. Journal of Informetrics, 2014, 8(2): 295-309.
14 刘萍, 郑凯伦, 邹德安. 基于LDA模型的科研合作推荐研究[J]. 情报理论与实践, 2015, 38(9): 79-85.
15 吕伟民, 王小梅, 韩涛. 结合链路预测和ET机器学习的科研合作推荐方法研究[J]. 数据分析与知识发现, 2017, 1(4): 38-45.
16 余传明, 龚雨田, 赵晓莉, 等. 基于多特征融合的金融领域科研合作推荐研究[J]. 数据分析与知识发现, 2017, 1(8): 39-47.
17 张金柱, 于文倩, 刘菁婕, 等. 基于网络表示学习的科研合作预测研究[J]. 情报学报, 2018, 37(2): 132-139.
18 王玙, 高琳. 基于社交圈的在线社交网络朋友推荐算法[J]. 计算机学报, 2014, 37(4): 801-808. |
|
|
|
