Exploring financially constrained small- and medium-sized enterprises based on a multi-relation translational graph attention network
Affiliation(s): College of Computer Science and Technology, Zhejiang University, Hangzhou 310000, China; MYbank, Ant Group, Hangzhou 310000, China; Department of Ant Intelligent Engine Technology, Ant Group, Hangzhou 310000, China; School of Computer and Information Engineering, Zhejiang Gongshang University, Hangzhou 310000, China; less
Received: 2022-04-14
Accepted: 2023-03-25
Available online: 2023-03-25
Abstract
(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., and SMEs' , 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 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.
京公网安备 11010502051620号
