ABSTRACT
Default risk assessment for small companies is a tough problem in financial services. Recent efforts utilize advanced Heterogeneous Graph Neural Networks (HGNNs) with metapaths to exploit interactive features in corporate activities for risk analysis. However, few works are proposed for commercial banks. Given a real financial graph, how to detect corporate default risks? We identify two challenges for the task. (1) Massive noisy connections hinder HGNNs to achieve strong results. (2) Multiple semantic connections greatly increase transitive default risk, while existing aggregation schemes do not leverage such connection patterns. In this work, we propose a novel Heterogeneous Graph Co-Attention Network for corporate default risk assessment. Our model takes advantage of collaborative metapaths to distill risky features by a co-attentive aggregation mechanism. First, the local attention score models the importance of neighbors under each metapath by holistic metapath context. Second, the global attention score fuse local attention scores to filter valuable/noisy signals. Then, pairwise importance learning aims to enhance attention scores of multi-metapath neighbors for risky feature distillation. Extensive experiments on large-scale banking datasets demonstrate the effectiveness of our method.
Supplemental Material
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).Google Scholar
- Wendong Bi, Bingbing Xu, Xiaoqian Sun, Zidong Wang, Huawei Shen, and Xueqi Cheng. 2022. Company-as-Tribe: Company financial risk assessment on tribe-style graph with hierarchical graph neural networks. In KDD. 2712--2720.Google Scholar
- Wendong Bi, Bingbing Xu, Xiaoqian Sun, Li Xu, Huawei Shen, and Xueqi Cheng. 2023. Predicting the silent majority on graphs: Knowledge transferable graph neural network. In WWW. 274--285.Google Scholar
- Dawei Cheng, Yi Tu, Zhen-Wei Ma, Zhibin Niu, and Liqing Zhang. 2019. Risk assessment for networked-guarantee loans using high-order graph attention representation. In IJCAI. 5822--5828.Google Scholar
- Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014).Google ScholarDigital Library
- Aaron Clauset, Cosma Rohilla Shalizi, and Mark EJ Newman. 2009. Power-law distributions in empirical data. SIAM review, Vol. 51, 4 (2009), 661--703.Google Scholar
- Paulius Danenas and Gintautas Garsva. 2015. Selection of support vector machines based classifiers for credit risk domain. Expert Syst. Appl. , Vol. 42, 6 (2015), 3194--3204.Google ScholarDigital Library
- Bin Duan, Hao Tang, Wei Wang, Ziliang Zong, Guowei Yang, and Yan Yan. 2021. Audio-visual event localization via recursive fusion by joint co-attention. In WACV. 4013--4022.Google Scholar
- Shaohua Fan, Junxiong Zhu, Xiaotian Han, Chuan Shi, Linmei Hu, Biyu Ma, and Yongliang Li. 2019b. Metapath-guided heterogeneous graph neural network for intent recommendation. In KDD. 2478--2486.Google Scholar
- Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin. 2019a. Graph neural networks for social recommendation. In WWW. 417--426.Google Scholar
- Xinyu Fu, Jiani Zhang, Ziqiao Meng, and Irwin King. 2020. Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. In WWW. 2331--2341.Google Scholar
- Diego Garlaschelli and Maria I Loffredo. 2005. Structure and evolution of the world trade network. Physica A Stat. Mech. Appl. , Vol. 355, 1 (2005), 138--144.Google ScholarCross Ref
- Lingbing Guo, Zequn Sun, and Wei Hu. 2019. Learning to exploit long-term relational dependencies in knowledge graphs. In ICML. 2505--2514.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. NeurIPS , Vol. 30 (2017).Google Scholar
- Binbin Hu, Chuan Shi, Wayne Xin Zhao, and Philip S Yu. 2018. Leveraging meta-path based context for top-n recommendation with a neural co-attention model. In KDD. 1531--1540.Google Scholar
- Binbin Hu, Zhiqiang Zhang, Chuan Shi, Jun Zhou, Xiaolong Li, and Yuan Qi. 2019. Cash-out user detection based on attributed heterogeneous information network with a hierarchical attention mechanism. In AAAI, Vol. 33. 946--953.Google ScholarDigital Library
- Ziniu Hu, Yuxiao Dong, Kuansan Wang, and Yizhou Sun. 2020. Heterogeneous graph transformer. In WWW. 2704--2710.Google Scholar
- Mengda Huang, Yang Liu, Xiang Ao, Kuan Li, Jianfeng Chi, Jinghua Feng, Hao Yang, and Qing He. 2022. Auc-oriented graph neural network for fraud detection. In WWW. 1311--1321.Google Scholar
- Wei-Qiang Huang, Xin-Tian Zhuang, and Shuang Yao. 2009. A network analysis of the Chinese stock market. Physica A Stat. Mech. Appl. , Vol. 388, 14 (2009), 2956--2964.Google ScholarCross Ref
- Yugang Ji, Guanyi Chu, Xiao Wang, Chuan Shi, Jianan Zhao, and Junping Du. 2022. Prohibited item detection via risk graph structure learning. In WWW. 1434--1443.Google Scholar
- Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. In NeurIPS, Vol. 30. 3146--3154.Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR.Google Scholar
- Gang Kou, Yong Xu, Yi Peng, Feng Shen, Yang Chen, Kun Chang, and Shaomin Kou. 2021. Bankruptcy prediction for SMEs using transactional data and two-stage multiobjective feature selection. Decis. Support Syst. , Vol. 140 (2021), 113429.Google ScholarCross Ref
- Elisa Letizia and Fabrizio Lillo. 2019. Corporate payments networks and credit risk rating. EPJ Data Science, Vol. 8, 1 (2019), 21.Google ScholarCross Ref
- Boyu Li, Ting Guo, Yang Wang, Amir H Gandomi, and Fang Chen. 2021. Adaptive graph co-attention networks for traffic forecasting. In PAKDD. 263--276.Google Scholar
- Guohao Li, Chenxin Xiong, Ali Thabet, and Bernard Ghanem. 2020. Deepergcn: All you need to train deeper gcns. arXiv preprint arXiv:2006.07739 (2020).Google Scholar
- Can Liu, Li Sun, Xiang Ao, Jinghua Feng, Qing He, and Hao Yang. 2021. Intention-aware heterogeneous graph attention networks for fraud transactions detection. In KDD. 3280--3288.Google Scholar
- Yucheng Liu, Zipeng Gao, Xiangyang Liu, Pengfei Luo, Yang Yang, and Hui Xiong. 2023. QTIAH-GNN: Quantity and topology imbalance-aware heterogeneous graph neural network for bankruptcy prediction. In KDD. 1572--1582.Google Scholar
- Yiding Liu, Yulong Gu, Zhuoye Ding, Junchao Gao, Ziyi Guo, Yongjun Bao, and Weipeng Yan. 2020b. Decoupled graph convolution network for inferring substitutable and complementary items. In CIKM. 2621--2628.Google Scholar
- Zhiwei Liu, Yingtong Dou, Philip S Yu, Yutong Deng, and Hao Peng. 2020a. Alleviating the inconsistency problem of applying graph neural network to fraud detection. In SIGIR. 1569--1572.Google Scholar
- Jiasen Lu, Jianwei Yang, Dhruv Batra, and Devi Parikh. 2016. Hierarchical question-image co-attention for visual question answering. NeurIPS , Vol. 29 (2016).Google Scholar
- Yi-Ju Lu and Cheng-Te Li. 2020. GCAN: Graph-aware co-attention networks for explainable fake news detection on social media. In ACL. 505--514.Google Scholar
- Qingsong Lv, Ming Ding, Qiang Liu, Yuxiang Chen, Wenzheng Feng, Siming He, Chang Zhou, Jianguo Jiang, Yuxiao Dong, and Jie Tang. 2021. Are we really making much progress? Revisiting, benchmarking and refining heterogeneous graph neural networks. In KDD. 1150--1160.Google Scholar
- Duy-Kien Nguyen and Takayuki Okatani. 2018. Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In CVPR. 6087--6096.Google Scholar
- Jie Sun, Jie Lang, Hamido Fujita, and Hui Li. 2018. Imbalanced enterprise credit evaluation with DTE-SBD: Decision tree ensemble based on SMOTE and bagging with differentiated sampling rates. Inf. Sci. , Vol. 425 (2018), 76--91.Google ScholarDigital Library
- Yizhou Sun and Jiawei Han. 2013. Mining heterogeneous information networks: a structural analysis approach. SIGKDD Explor. Newsl. , Vol. 14, 2 (2013), 20--28.Google ScholarDigital Library
- Yizhou Sun, Jiawei Han, Xifeng Yan, Philip S Yu, and Tianyi Wu. 2011. Pathsim: Meta path-based top-k similarity search in heterogeneous information networks. VLDB, Vol. 4, 11 (2011), 992--1003.Google ScholarDigital Library
- Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, and Suhang Wang. 2020. Transferring robustness for graph neural network against poisoning attacks. In WSDM. 600--608.Google Scholar
- Petar Velivc ković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In ICLR.Google Scholar
- Can Wang, Sheng Zhou, Kang Yu, Defang Chen, Bolang Li, Yan Feng, and Chun Chen. 2022b. Collaborative knowledge distillation for heterogeneous information network embedding. In WWW. 1631--1639.Google Scholar
- Heyuan Wang, Tengjiao Wang, Shun Li, Shijie Guan, Jiayi Zheng, and Wei Chen. 2022a. Heterogeneous interactive snapshot network for review-enhanced stock profiling and recommendation. In IJCAI. 3962--3969.Google Scholar
- Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Romain Garnier, and Neil M Robertson. 2019a. Ranked list loss for deep metric learning. In CVPR. 5207--5216.Google Scholar
- Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Yanfang Ye, Peng Cui, and Philip S Yu. 2019b. Heterogeneous graph attention network. In WWW. 2022--2032.Google Scholar
- Yuchen Wang, Jinghui Zhang, Zhengjie Huang, Weibin Li, Shikun Feng, Ziheng Ma, Yu Sun, Dianhai Yu, Fang Dong, Jiahui Jin, et al. 2023. Label information enhanced fraud detection against low homophily in graphs. In WWW. 406--416.Google Scholar
- Shaopeng Wei, Jia Lv, Yu Guo, Qing Yang, Xingyan Chen, Yu Zhao, Qing Li, Fuzhen Zhuang, and Gang Kou. 2024. Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networks. Inf. Sci. (2024), 120081.Google Scholar
- Chao-Yuan Wu, R Manmatha, Alexander J Smola, and Philipp Krahenbuhl. 2017. Sampling matters in deep embedding learning. In ICCV. 2840--2848.Google Scholar
- Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Peng He, Paul Weng, Han Gao, and Guihai Chen. 2019. Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems. In WWW. 2091--2102.Google Scholar
- Shuo Yang, Zhiqiang Zhang, Jun Zhou, Yang Wang, Wang Sun, Xingyu Zhong, Yanming Fang, Quan Yu, and Yuan Qi. 2020. Financial risk analysis for SMEs with graph-based supply chain mining. In IJCAI. 4661--4667.Google Scholar
- Xiaocheng Yang, Mingyu Yan, Shirui Pan, Xiaochun Ye, and Dongrui Fan. 2023. Simple and efficient heterogeneous graph neural network. In AAAI, Vol. 37. 10816--10824.Google ScholarDigital Library
- Ching-Chiang Yeh, Der-Jang Chi, and Yi-Rong Lin. 2014. Going-concern prediction using hybrid random forests and rough set approach. Inf. Sci. , Vol. 254 (2014), 98--110.Google ScholarDigital Library
- Mengmei Zhang, Xiao Wang, Meiqi Zhu, Chuan Shi, Zhiqiang Zhang, and Jun Zhou. 2022. Robust heterogeneous graph neural networks against adversarial attacks. In AAAI, Vol. 36. 4363--4370.Google ScholarCross Ref
- Jianan Zhao, Xiao Wang, Chuan Shi, Binbin Hu, Guojie Song, and Yanfang Ye. 2021. Heterogeneous graph structure learning for graph neural networks. In AAAI, Vol. 35. 4697--4705.Google ScholarCross Ref
- Jiawei Zheng, Qianli Ma, Hao Gu, and Zhenjing Zheng. 2021b. Multi-view denoising graph auto-encoders on heterogeneous information networks for cold-start recommendation. In KDD. 2338--2348.Google Scholar
- Yizhen Zheng, Vincent Lee, Zonghan Wu, and Shirui Pan. 2021a. Heterogeneous graph attention network for small and medium-sized enterprises bankruptcy prediction. In PAKDD. 140--151.Google Scholar
- Qiwei Zhong, Yang Liu, Xiang Ao, Binbin Hu, Jinghua Feng, Jiayu Tang, and Qing He. 2020. Financial defaulter detection on online credit payment via multi-view attributed heterogeneous information network. In WWW. 785--795.Google Scholar
Index Terms
- Collaborative Metapath Enhanced Corporate Default Risk Assessment on Heterogeneous Graph
Recommendations
Default Risk and Option Returns
This paper studies the effects of default risk on expected equity option returns. In the cross-section, expected delta-hedged equity option returns have a negative relation with default risk measured by credit ratings or default probability. In the time ...
Global diversification, hedging diversification, and default risk in bank equity: an option-pricing model
Many banks diversify their operations, either across different national markets (global diversification), across different borrowers by offsetting credit risks (hedging diversification), or both. Can multiple diversifications provide greater safety for ...
Do Stock Returns Really Decrease with Default Risk? New International Evidence
This study constructs a novel data set of bankruptcy filings for a large sample of non-U.S. firms in 14 developed markets and sheds new light on the cross-sectional relation between default risk and stock returns. Using the reduced-form approach of ...
Comments