Bin Wu
ABSTRACT
Fraudsters in the real world frequently add more legitimate links while concealing their direct ones with other fraudsters, leading to heterophily in fraud graphs, which is a problem that most GNN-based techniques are not built to solve. Several works have been proposed to tackle the issue from the spatial domain. However, researches on addressing the heterophily problem in the spectral domain are still limited due to a lack of understanding of spectral energy distribution in graphs with heterophily. In this paper, we analyze the spectral distribution with different heterophily degrees and observe that the heterophily of fraud nodes leads to the spectral energy moving from low-frequency to high-frequency. Further, we verify that splitting graphs using heterophilic and homophilic edges can obtain more significant expressions of signals in different frequency bands. The observation drives us to propose the spectral graph neural network, SplitGNN, to capture signals for fraud detection against heterophily. SplitGNN uses an edge classifier to split the original graph and adopts flexible band-pass graph filters to learn representations. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method. The code and data are available at https://github.com/Split-GNN/SplitGNN.
- Deyu Bo, Chuan Shi, Lele Wang, and Renjie Liao. 2023 a. Specformer: Spectral Graph Neural Networks Meet Transformers. In The Eleventh International Conference on Learning Representations.Google Scholar
- Deyu Bo, Xiao Wang, Yang Liu, Yuan Fang, Yawen Li, and Chuan Shi. 2023 b. A Survey on Spectral Graph Neural Networks. arxiv: 2302.05631 [cs]Google Scholar
- Deyu Bo, Xiao Wang, Chuan Shi, and Huawei Shen. 2021. Beyond Low-Frequency Information in Graph Convolutional Networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 3950--3957.Google ScholarCross Ref
- Ziwei Chai, Siqi You, Yang Yang, Shiliang Pu, Jiarong Xu, Haoyang Cai, and Weihao Jiang. 2022. Can Abnormality Be Detected by Graph Neural Networks ?. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI), Vienna, Austria. 23--29.Google ScholarCross Ref
- Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A Scalable Tree Boosting System. In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining. 785--794.Google ScholarDigital Library
- Eli Chien, Jianhao Peng, Pan Li, and Olgica Milenkovic. 2021. Adaptive Universal Generalized PageRank Graph Neural Network. In International Conference on Learning Representations.Google Scholar
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. Advances in neural information processing systems, Vol. 29 (2016).Google Scholar
- Yingtong Dou, Zhiwei Liu, Li Sun, Yutong Deng, Hao Peng, and Philip S. Yu. 2020. Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters. Proceedings of the 29th ACM International Conference on Information & Knowledge Management (Oct. 2020), 315--324. https://doi.org/10.1145/3340531.3411903 arxiv: 2008.08692Google ScholarDigital Library
- Yuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu, Huamin Feng, and Yongdong Zhang. 2023. Addressing Heterophily in Graph Anomaly Detection : A Perspective of Graph Spectrum. In Proceedings of the ACM Web Conference 2023 (WWW '23). Association for Computing Machinery, New York, NY, USA, 1528--1538. https://doi.org/10.1145/3543507.3583268Google ScholarDigital Library
- David K. Hammond, Pierre Vandergheynst, and Rémi Gribonval. 2011. Wavelets on Graphs via Spectral Graph Theory. Applied and Computational Harmonic Analysis, Vol. 30, 2 (March 2011), 129--150. https://doi.org/10.1016/j.acha.2010.04.005Google ScholarCross Ref
- Mingguo He, Zhewei Wei, and Hongteng Xu. 2021. Bernnet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation. Advances in Neural Information Processing Systems, Vol. 34 (2021), 14239--14251.Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Conference Track Proceedings. OpenReview.net.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). arxiv: 2006.07739Google Scholar
- Jianping Li, Yanpeng Chang, Yinghui Wang, and Xiaoqian Zhu. 2023. Tracking down Financial Statement Fraud by Analyzing the Supplier-Customer Relationship Network. Computers & Industrial Engineering, Vol. 178 (April 2023), 109118. https://doi.org/10.1016/j.cie.2023.109118Google ScholarDigital Library
- Lin Liao, Guanting Chen, and Dengjin Zheng. 2019. Corporate Social Responsibility and Financial Fraud: Evidence from China. Accounting & Finance, Vol. 59, 5 (2019), 3133--3169.Google ScholarCross Ref
- Can Liu, Li Sun, Xiang Ao, Jinghua Feng, Qing He, and Hao Yang. 2021b. Intention-Aware Heterogeneous Graph Attention Networks for Fraud Transactions Detection. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. ACM, Virtual Event Singapore, 3280--3288. https://doi.org/10.1145/3447548.3467142Google ScholarDigital Library
- Yang Liu, Xiang Ao, Zidi Qin, Jianfeng Chi, Jinghua Feng, Hao Yang, and Qing He. 2021a. Pick and Choose : A GNN-based Imbalanced Learning Approach for Fraud Detection. In Proceedings of the Web Conference 2021 (WWW '21). Association for Computing Machinery, New York, NY, USA, 3168--3177. https://doi.org/10.1145/3442381.3449989Google ScholarDigital Library
- Zhiwei Liu, Yingtong Dou, Philip S. Yu, Yutong Deng, and Hao Peng. 2020. Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (July 2020), 1569--1572. https://doi.org/10.1145/3397271.3401253 arxiv: 2005.00625Google ScholarDigital Library
- Hoang NT and Takanori Maehara. 2019. Revisiting Graph Neural Networks : All We Have Is Low-Pass Filters. https://doi.org/10.48550/arXiv.1905.09550 arxiv: 1905.09550 [cs, math, stat]Google Scholar
- Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, and Luca Antiga. 2019. Pytorch: An Imperative Style, High-Performance Deep Learning Library. Advances in neural information processing systems, Vol. 32 (2019).Google Scholar
- Hao Peng, Ruitong Zhang, Yingtong Dou, Renyu Yang, Jingyi Zhang, and Philip S. Yu. 2021. Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks. ACM Transactions on Information Systems (TOIS), Vol. 40, 4 (2021), 1--46.Google ScholarDigital Library
- Nathanaël Perraudin, Johan Paratte, David Shuman, Lionel Martin, Vassilis Kalofolias, Pierre Vandergheynst, and David K. Hammond. 2014. GSPBOX : A Toolbox for Signal Processing on Graphs. https://arxiv.org/abs/1408.5781v2.Google Scholar
- Fengzhao Shi, Yanan Cao, Yanmin Shang, Yuchen Zhou, Chuan Zhou, and Jia Wu. 2022. H2-FDetector : A GNN-based Fraud Detector with Homophilic and Heterophilic Connections. In Proceedings of the ACM Web Conference 2022 (WWW '22). Association for Computing Machinery, New York, NY, USA, 1486--1494. https://doi.org/10.1145/3485447.3512195Google ScholarDigital Library
- Jianheng Tang, Jiajin Li, Ziqi Gao, and Jia Li. 2022. Rethinking Graph Neural Networks for Anomaly Detection. In Proceedings of the 39th International Conference on Machine Learning. PMLR, 21076--21089.Google Scholar
- Petar Veliv cković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations.Google Scholar
- Daixin Wang, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, Shuang Yang, and Yuan Qi. 2019. A Semi-Supervised Graph Attentive Network for Financial Fraud Detection. In 2019 IEEE International Conference on Data Mining (ICDM ). 598--607. https://doi.org/10.1109/ICDM.2019.00070Google ScholarCross Ref
- Minjie Yu Wang. 2019. Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs. In ICLR Workshop on Representation Learning on Graphs and Manifolds.Google Scholar
- Bingbing Xu, Huawei Shen, Qi Cao, Yunqi Qiu, and Xueqi Cheng. 2018. Graph Wavelet Neural Network. In International Conference on Learning Representations.Google Scholar
- Xuebin Zheng, Bingxin Zhou, Ming Li, Yu Guang Wang, and Junbin Gao. 2023. MathNet : Haar-like Wavelet Multiresolution Analysis for Graph Representation Learning. Knowledge-Based Systems, Vol. 273 (Aug. 2023), 110609. https://doi.org/10.1016/j.knosys.2023.110609Google ScholarDigital Library
- Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. 2020. Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs. Advances in Neural Information Processing Systems, Vol. 33 (2020), 7793--7804.Google Scholar
Index Terms
- SplitGNN: Spectral Graph Neural Network for Fraud Detection against Heterophily
Recommendations
H2-FDetector: A GNN-based Fraud Detector with Homophilic and Heterophilic Connections
WWW '22: Proceedings of the ACM Web Conference 2022In the fraud graph, fraudsters often interact with a large number of benign entities to hide themselves. So, there are not only the homophilic connections formed by the same label nodes (similar nodes), but also the heterophilic connections formed by ...
Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum
WWW '23: Proceedings of the ACM Web Conference 2023Graph anomaly detection (GAD) suffers from heterophily — abnormal nodes are sparse so that they are connected to vast normal nodes. The current solutions upon Graph Neural Networks (GNNs) blindly smooth the representation of neiboring nodes, thus ...
Group-based Fraud Detection Network on e-Commerce Platforms
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAlong with the rapid technological and commercial innovation on the e-commerce platforms, there are an increasing number of frauds that bring great harm to these platforms. Many frauds are conducted by organized groups of fraudsters for higher efficiency ...
Comments