基于多关系平移图注意力网络的需融中小企业挖掘方法

梁倩乔; 卫华; 吴亚熙; 韦峰; 赵登; 何建衫; 郑小林; 马国芳; 韩冰

doi:10.1631/FITEE.2200151

Your Location：

Home >

Browse articles >

基于多关系平移图注意力网络的需融中小企业挖掘方法

常规文章 | Updated：2023-03-24

- 基于多关系平移图注意力网络的需融中小企业挖掘方法
- Exploring financially constrained small- and medium-sized enterprises based on a multi-relation translational graph attention network
- 信息与电子工程前沿（英文） 2023年24卷第3期页码：388-402
- Affiliations：
  
  1.College of Computer Science and Technology, Zhejiang University, Hangzhou 310000, China
  2.MYbank, Ant Group, Hangzhou 310000, China
  3.Department of Ant Intelligent Engine Technology, Ant Group, Hangzhou 310000, China
  4.School of Computer and Information Engineering, Zhejiang Gongshang University, Hangzhou 310000, China
- Author bio：
  
  ‡ Corresponding author
- Funds：
  
  National Natural Science Foundation of China(72192823);"Ten Thousand Talents Program" of Zhejiang Province for Leading Experts(2021R52001);Cooperation Project of MYbank, Ant Group
- DOI：10.1631/FITEE.2200151
  中图分类号： TP391
- 收稿：2022-04-14，
  
  录用：2022-12-01，
  
  纸质出版：2023-03-0
- Accepted：
Scan QR Code
梁倩乔, 卫华, 吴亚熙, 等. 基于多关系平移图注意力网络的需融中小企业挖掘方法[J]. 信息与电子工程前沿（英文）, 2023,24(3):388-402.

Qianqiao LIANG, Hua WEI, Yaxi WU, et al. Exploring financially constrained small- and medium-sized enterprises based on a multi-relation translational graph attention network[J]. Frontiers of Information Technology & Electronic Engineering, 2023, 24(3): 388-402.
梁倩乔, 卫华, 吴亚熙, 等. 基于多关系平移图注意力网络的需融中小企业挖掘方法[J]. 信息与电子工程前沿（英文）, 2023,24(3):388-402. DOI： 10.1631/FITEE.2200151.

Qianqiao LIANG, Hua WEI, Yaxi WU, et al. Exploring financially constrained small- and medium-sized enterprises based on a multi-relation translational graph attention network[J]. Frontiers of Information Technology & Electronic Engineering, 2023, 24(3): 388-402. DOI： 10.1631/FITEE.2200151.

摘要

需融企业挖掘任务指挖掘财务困难、需要融资的中小企业，其有利于金融机构帮助中小企业的发展，在金融领域中发挥着越来越重要的作用。本文首先深入分析中小企业的融资需求在企业社交网络中的传递现象，从而提供了一个利用企业社交网络来提升需融企业挖掘有效性的想法，即学习企业社交网络中企业节点的表征并利用该表征挖掘需融企业。然而，该想法面临两种异构性挑战，即融资需求在不同关系下的传递异构性和中小企业在不同关系类型下的行为模式异构性。为了应对这些挑战，本文提出一种基于多关系平移图注意力网络的需融企业挖掘方法。该方法不仅基于一种新颖的实体-关系组合算子来对不同关系类型下的融资需求传递异构性进行建模，还基于本文所设计的关系超平面平移机制来获得中小企业在不同关系类型下的表征，以区分中小企业在不同关系类型下的异构行为模式。最后，本文在两个大型真实数据集上进行大量实验，实验结果证明了所提方法在需融企业挖掘任务中优于最先进的方法。

Abstract

Financing needs exploration (FNE)

which explores financially constrained small- and medium-sized enterprises (SMEs)

has become increasingly important in industry for financial institutions to facilitate SMEs' development. In this paper

we first perform an insightful exploratory analysis to exploit the transfer phenomenon of financing needs among SMEs

which motivates us to fully exploit the multi-relation enterprise social network for boosting the effectiveness of FNE. The main challenge lies in modeling two kinds of heterogeneity

i.e.

transfer heterogeneity and SMEs' behavior heterogeneity

under different relation types simultaneously. To address these challenges

we propose a graph neural network named Multi-relation tRanslatIonal GrapH aTtention network (M-RIGHT)

which not only models the transfer heterogeneity of financing needs along different relation types based on a novel entity–relation composition operator but also enables heterogeneous SMEs' representations based on a translation mechanism on relational hyperplanes to distinguish SMEs' heterogeneous behaviors under different relation types. Extensive experiments on two large-scale real-world datasets demonstrate M-RIGHT's superiority over the state-of-the-art methods in the FNE task.

关键词

Keywords

references

Angilella S , Mazzù S , 2015 . The financing of innovative SMEs: a multicriteria credit rating model . Eur J Oper Res , 244 ( 2 ): 540 - 554 . doi: 10.1016/j.ejor.2015.01.033 http://doi.org/10.1016/j.ejor.2015.01.033

Bordes A , Usunier N , García-Durán A , et al. , 2013 . Translating embeddings for modeling multi-relational data . Proc 26 th Int Conf on Neural Information Processing Systems , p. 2787 - 2795 . doi: 10.5555/2999792.2999923 http://doi.org/10.5555/2999792.2999923

Ceptureanu EG , Ceptureanu S , Herteliu C , 2021 . Evidence regarding external financing in manufacturing MSEs using partial least squares regression . Ann Oper Res , 299 ( 1-2 ): 1189 - 1202 . doi: 10.1007/s10479-019-03291-2 http://doi.org/10.1007/s10479-019-03291-2

Chen XF , Zhao YD , Wei ZF , et al. , 2020 . Intelligent identification of potential customers for electricity substitution . In: Tallón-Ballesteros AJ (Ed.), Fuzzy Systems and Data Mining, VI. IOS Press , p. 168 - 179 . doi: 10.3233/FAIA200697 http://doi.org/10.3233/FAIA200697

Cheng HT , Koc L , Harmsen J , et al. , 2016 . Wide & deep learning for recommender systems . Proc 1 st Workshop on Deep Learning for Recommender Systems , p. 7 - 10 . doi: 10.1145/2988450.2988454 http://doi.org/10.1145/2988450.2988454

Dettmers T , Minervini P , Stenetorp P , et al. , 2018 . Convolutional 2D knowledge graph embeddings . Proc 32 nd AAAI Conf on Artificial Intelligence , p. 1811 - 1818 . doi: 10.1609/aaai.v32i1.11573 http://doi.org/10.1609/aaai.v32i1.11573

Dong YX , Chawla NV , Swami A , 2017 . metapath2vec: scalable representation learning for heterogeneous networks . Proc 23 rd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , p. 135 - 144 . doi: 10.1145/3097983.3098036 http://doi.org/10.1145/3097983.3098036

Duan GL , Ma X , 2018 . A coupon usage prediction algorithm based on XGBoost . Proc 14 th Int Conf on Natural Computation, Fuzzy Systems and Knowledge Discovery , p. 178 - 183 . doi: 10.1109/FSKD.2018.8686924 http://doi.org/10.1109/FSKD.2018.8686924

Fu XY , Zhang JN , Meng ZQ , et al. , 2020 . MAGNN: meta- path aggregated graph neural network for heterogeneous graph embedding . Proc Web Conf , p. 2331 - 2341 . doi: 10.1145/3366423.3380297 http://doi.org/10.1145/3366423.3380297

Graesch JP , Hensel-Börner S , Henseler J , 2021 . Information technology and marketing: an important partnership for decades . Ind Manag Data Syst , 121 ( 1 ): 123 - 157 . doi: 10.1108/IMDS-08-2020-0510 http://doi.org/10.1108/IMDS-08-2020-0510

Grover A , Leskovec J , 2016 . node2vec: scalable feature learning for networks . Proc 22 nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , p. 855 - 864 . doi: 10.1145/2939672.2939754 http://doi.org/10.1145/2939672.2939754

Guo HF , Tang RM , Ye YM , et al. , 2017 . DeepFM: a factorization-machine based neural network for CTR prediction . Proc 26 th Int Joint Conf on Artificial Intelligence , p. 1725 - 1731 . doi: 10.24963/ijcai.2017/239 http://doi.org/10.24963/ijcai.2017/239

Hamilton WL , Ying Z , Leskovec J , 2017 . Inductive representation learning on large graphs . Proc 31 st Int Conf on Neural Information Processing Systems , p. 1025 - 1035 . doi: 10.5555/3294771.3294869 http://doi.org/10.5555/3294771.3294869

Jeon H , 2021 . Investment and financing decisions in the presence of time-to-build . Eur J Oper Res , 288 ( 3 ): 1068 - 1084 . doi: 10.1016/j.ejor.2020.06.034 http://doi.org/10.1016/j.ejor.2020.06.034

Ji SX , Pan SR , Cambria E , et al. , 2022 . A survey on knowledge graphs: representation, acquisition, and applications . IEEE Trans Neur Netw Learn Syst , 33 ( 2 ): 494 - 514 . doi: 10.1109/TNNLS.2021.3070843 http://doi.org/10.1109/TNNLS.2021.3070843

Kipf TN , Welling M , 2017 . Semi-supervised classification with graph convolutional networks . Proc 5 th Int Conf on Learning Representations , p. 1 - 10 .

Kshetri N , 2016 . Big data's role in expanding access to financial services in China . Int J Inform Manag , 36 ( 3 ): 297 - 308 . doi: 10.1016/j.ijinfomgt.2015.11.014 http://doi.org/10.1016/j.ijinfomgt.2015.11.014

Lessmann S , Haupt J , Coussement K , et al. , 2021 . Targeting customers for profit: an ensemble learning framework to support marketing decision-making . Inform Sci , 557 : 286 - 301 . doi: 10.1016/j.ins.2019.05.027 http://doi.org/10.1016/j.ins.2019.05.027

Li ZF , Liu H , Zhang ZL , et al. , 2022 . Learning knowledge graph embedding with heterogeneous relation attention networks . IEEE Trans Neur Netw Learn Syst , 33 ( 8 ): 3961 - 3973 . doi: 10.1109/TNNLS.2021.3055147 http://doi.org/10.1109/TNNLS.2021.3055147

Liao HF , Hu J , Li TR , et al. , 2022 . Deep linear graph attention model for attributed graph clustering . Knowl-Based Syst , 246 : 108665 . doi: 10.1016/j.knosys.2022.108665 http://doi.org/10.1016/j.knosys.2022.108665

Luo Y , Deng TY , Wei Q , et al. , 2021 . Optimal financing decision in a contract food supply chain with capital constraint . Complexity , 2021 : 8925102 . doi: 10.1155/2021/8925102 http://doi.org/10.1155/2021/8925102

Maas AL , Hannun AY , Ng AY , 2013 . Rectifier nonlinearities improve neural network acoustic models . Proc 30 th Int Conf on Machine Learning , p. 1 - 6 .

Mikolov T , Chen K , Corrado G , et al. , 2013 . Efficient estimation of word representations in vector space . Proc 1 st Int Conf on Learning Representations , p. 1 - 10 .

Nickel M , Rosasco L , Poggio T , 2016 . Holographic embeddings of knowledge graphs . Proc 30 th AAAI Conf on Artificial Intelligence , p. 1955 - 1961 . doi: 10.5555/3016100.3016172 http://doi.org/10.5555/3016100.3016172

Perozzi B , Al-Rfou R , Skiena S , 2014 . DeepWalk: online learning of social representations . Proc 20 th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , p. 701 - 710 . doi: 10.1145/2623330.2623732 http://doi.org/10.1145/2623330.2623732

Rogic S , Kascelan L , 2019 . Customer value prediction in direct marketing using hybrid support vector machine rule extraction method . Proc 23 rd European Conf on Advances in Databases and Information Systems , p. 283 - 294 . doi: 10.1007/978-3-030-30278-8_30 http://doi.org/10.1007/978-3-030-30278-8_30

Rogić S , Kašćelan L , Pejić Bach M , 2022 . Customer response model in direct marketing: solving the problem of unbalanced dataset with a balanced support vector machine . J Theor Appl Electron Commer Res , 17 ( 3 ): 1003 - 1018 . doi: 10.3390/jtaer17030051 http://doi.org/10.3390/jtaer17030051

Sadeghian A , Armandpour M , Colas A , et al. , 2021 . ChronoR: rotation based temporal knowledge graph embedding . Proc AAAI Conf on Artificial Intelligence , p. 6471 - 6479 . doi: 10.1609/aaai.v35i7.16802 http://doi.org/10.1609/aaai.v35i7.16802

Schlichtkrull M , Kipf TN , Bloem P , et al. , 2018 . Modeling relational data with graph convolutional networks . Proc 15 th Int Conf on Semantic Web Conf , p. 593 - 607 . doi: 10.1007/978-3-319-93417-4_38 http://doi.org/10.1007/978-3-319-93417-4_38

Shang C , Tang Y , Huang J , et al. , 2019 . End-to-end structure-aware convolutional networks for knowledge base completion . Proc AAAI Conf on Artificial Intelligence , p. 3060 - 3067 . doi: 10.1609/aaai.v33i01.33013060 http://doi.org/10.1609/aaai.v33i01.33013060

Shi Y , Gui H , Zhu Q , et al. , 2018a . ASPEM: embedding learning by aspects in heterogeneous information networks . Proc SIAM Int Conf on Data Mining , p. 144 - 152 . doi: 10.1137/1.9781611975321.16 http://doi.org/10.1137/1.9781611975321.16

Shi Y , Zhu Q , Guo F , et al. , 2018b . Easing embedding learning by comprehensive transcription of heterogeneous information networks . Proc 24 th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining , p. 2190 - 2199 . doi: 10.1145/3219819.3220006 http://doi.org/10.1145/3219819.3220006

Sun ZQ , Deng ZH , Nie JY , et al. , 2019 . Rotate: knowledge graph embedding by relational rotation in complex space . Proc 7 th Int Conf on Learning Representations , p. 1 - 10 .

Tang J , Qu M , Mei QZ , 2015 . PTE: predictive text embedding through large-scale heterogeneous text networks . Proc 21 st ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , p. 1165 - 1174 . doi: 10.1145/2783258.2783307 http://doi.org/10.1145/2783258.2783307

Tian Z , Hassan AFS , Razak NHA , 2018 . Big data and SME financing in China . J Phys Conf Ser , 1018 : 012002 . doi: 10.1088/1742-6596/1018/1/012002 http://doi.org/10.1088/1742-6596/1018/1/012002

Trouillon T , Welbl J , Riedel S , et al. , 2016 . Complex embeddings for simple link prediction . Proc 33 rd Int Conf on Machine Learning , p. 2071 - 2080 . doi: 10.5555/3045390.3045609 http://doi.org/10.5555/3045390.3045609

Vashishth S , Sanyal S , Nitin V , et al. , 2020a . Composition-based multi-relational graph convolutional networks . Proc 8 th Int Conf on Learning Representations , p. 1 - 10 .

Vashishth S , Sanyal S , Nitin V , et al. , 2020b . InteractE: improving convolution-based knowledge graph embeddings by increasing feature interactions . Proc AAAI Conf on Artificial Intelligence , p. 3009 - 3016 . doi: 10.1609/aaai.v34i03.5694 http://doi.org/10.1609/aaai.v34i03.5694

Veličković P , Cucurull G , Casanova A , et al. , 2018 . Graph attention networks . Proc 6th Int Conf on Learning Representations , p. 1 - 10 .

Wang X , Zhang YD , Shi C , 2019 . Hyperbolic heterogeneous information network embedding . Proc AAAI Conf on Artificial Intelligence , p. 5337 - 5344 . doi: 10.1609/aaai.v33i01.33015337 http://doi.org/10.1609/aaai.v33i01.33015337

Wang Y , Jing CF , Xu SS , et al. , 2022 . Attention based spatiotemporal graph attention networks for traffic flow forecasting . Inform Sci , 607 : 869 - 883 . doi: 10.1016/j.ins.2022.05.127 http://doi.org/10.1016/j.ins.2022.05.127

Wang Z , Zhang JW , Feng JL , et al. , 2014 . Knowledge graph embedding by translating on hyperplanes . Proc 28 th AAAI Conf on Artificial Intelligence , p. 1112 - 1119 . doi: 10.5555/2893873.2894046 http://doi.org/10.5555/2893873.2894046

Wu ZH , Pan SR , Chen FW , et al. , 2021 . A comprehensive survey on graph neural networks . IEEE Trans Neur Netw Learn Syst , 32 ( 1 ): 4 - 24 . doi: 10.1109/TNNLS.2020.2978386 http://doi.org/10.1109/TNNLS.2020.2978386

Xu KYL , Hu WH , Leskovec J , et al. , 2019 . How powerful are graph neural networks? Proc 7 th Int Conf on Learning Representations , p. 1 - 10 .

Xu ZP , Meisami A , Tewari A , 2021 . Decision making problems with funnel structure: a multi-task learning approach with application to email marketing campaigns . Proc 24 th Int Conf on Artificial Intelligence and Statistics , p. 127 - 135 .

Yang BS , Yih SWT , He XD , et al. , 2015 . Embedding entities and relations for learning and inference in knowledge bases . Proc 3 rd Int Conf on Learning Representations , p. 1 - 10 .

Yang C , Xiao YX , Zhang Y , et al. , 2022 . Heterogeneous network representation learning: a unified framework with survey and benchmark . IEEE Trans Knowl Data Eng , 34 ( 10 ): 4854 - 4873 . doi: 10.1109/TKDE.2020.3045924 http://doi.org/10.1109/TKDE.2020.3045924

Yang S , Zhang ZQ , Zhou J , et al. , 2020 . Financial risk analysis for SMEs with graph-based supply chain mining . Proc 29 th Int Joint Conf on Artificial Intelligence , p. 4661 - 4667 . doi: 10.24963/ijcai.2020/643 http://doi.org/10.24963/ijcai.2020/643

Ye R , Li X , Fang YJ , et al. , 2019 . A vectorized relational graph convolutional network for multi-relational network alignment . Proc 28 th Int Joint Conf on Artificial Intelligence , p. 4135 - 4141 . doi: 10.24963/ijcai.2019/574 http://doi.org/10.24963/ijcai.2019/574

Yu PY , Fu CF , Yu YW , et al. , 2022 . Multiplex heterogeneous graph convolutional network . Proc 28 th ACM SIGKDD Conf on Knowledge Discovery and Data Mining , p. 2377 - 2387 . doi: 10.1145/3534678.3539482 http://doi.org/10.1145/3534678.3539482

Zhang B , Wang LQ , Li YY , 2021 . Precision marketing method of e-commerce platform based on clustering algorithm . Complexity , 2021 : 5538677 . doi: 10.1155/2021/5538677 http://doi.org/10.1155/2021/5538677

Zhang WT , Fang Y , Liu ZM , et al. , 2022 . mg2vec: learning relationship-preserving heterogeneous graph representations via metagraph embedding . IEEE Trans Knowl Data Eng , 34 ( 3 ): 1317 - 1329 . doi: 10.1109/TKDE.2020.2992500 http://doi.org/10.1109/TKDE.2020.2992500

Zhao J , Wang X , Shi C , et al. , 2021 . Heterogeneous graph structure learning for graph neural networks . Proc AAAI Conf on Artificial Intelligence , p. 4697 - 4705 . doi: 10.1609/aaai.v35i5.16600 http://doi.org/10.1609/aaai.v35i5.16600

浏览量

110

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据