{"type":"ScholarlyArticle","title":"Can Abnormality be Detected by Graph Neural Networks?","authors":[{"name":"Ziwei Chai","slug":"ziwei-chai","given":"Ziwei","family":"Chai","affiliation":"Zhejiang University"},{"name":"Siqi You","slug":"siqi-you","given":"Siqi","family":"You","affiliation":"Zhejiang University"},{"name":"Yang Yang","slug":"yang-yang","given":"Yang","family":"Yang","affiliation":"Zhejiang University"},{"name":"Shiliang Pu","slug":"shiliang-pu","given":"Shiliang","family":"Pu","affiliation":"Hikvision Research Institute"},{"name":"Jiarong Xu","slug":"jiarong-xu","given":"Jiarong","family":"Xu","affiliation":"Fudan University"},{"name":"Haoyang Cai","slug":"haoyang-cai","given":"Haoyang","family":"Cai","affiliation":"Carnegie Mellon University"},{"name":"Weihao Jiang","slug":"weihao-jiang","given":"Weihao","family":"Jiang","affiliation":"Fudan University"}],"abstract":"Anomaly detection in graphs has attracted considerable interests in both academia and industry due to its wide applications in numerous domains ranging from finance to biology. Meanwhile, graph neural networks (GNNs) is emerging as a powerful tool for modeling graph data. A natural and fundamental question that arises here is: can abnormality be detected by graph neural networks?\r\n\r\nIn this paper, we aim to answer this question, which is nontrivial. As many existing works have explored, graph neural networks can be seen as filters for graph signals, with the favor of low frequency in graphs. In other words, GNN will smooth the signals of adjacent nodes. However, abnormality in a graph intuitively has the characteristic that it tends to be dissimilar to its neighbors, which are mostly normal samples. It thereby conflicts with the general assumption with traditional GNNs. To solve this, we propose a novel Adaptive Multi-frequency Graph Neural Network (AMNet), aiming to capture both low-frequency and high-frequency signals, and adaptively combine signals of different frequencies. Experimental  results on real-world datasets demonstrate that our model achieves a significant improvement comparing with several state-of-the-art baseline methods.","doi":"10.24963/ijcai.2022/270","url":"https://ijcai.org/proceedings/2022/270","pdf":"https://ijcai.org/proceedings/2022/0270.pdf","markdown":"https://ijcai.org/proceedings/2022/270.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/270","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Data Mining","track":"Main Track","number":270,"pages":{"first":1945,"last":1951},"keywords":["Data Mining: Mining Graphs","Data Mining: Networks"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986800","length_sec":84,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984943","length_sec":347,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Balcilar et al., 2021] Muhammet Balcilar, Guillaume Ren- ton, Pierre Héroux, Benoit Gaüzère, Sébastien Adam, and Paul Honeine. Analyzing the expressive power of graph neural networks in a spectral perspective. In ICLR, 2021.","title":"Analyzing the expressive power of graph neural networks in a spectral perspective","authors":"Muhammet Balcilar, Guillaume Renton, Pierre Héroux, Benoit Gaüzère, Sébastien Adam, Paul Honeine","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bruna et al., 2014] Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. Spectral networks and locally connected networks on graphs. In ICLR, 2014.","title":"Spectral networks and locally connected networks on graphs","authors":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann Lecun","year":"2014","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Defferrard et al., 2016] Michaël Defferrard, Xavier Bres- son, and Pierre Vandergheynst. Convolutional neural net- works on graphs with fast localized spectral filtering. In NIPS, 2016.","title":"Convolutional neural networks on graphs with fast localized spectral filtering","authors":"Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ding et al., 2019] Kaize Ding, Jundong Li, Rohit Bhanushali, and Huan Liu. Deep anomaly detection on attributed networks. In SDM, 2019.","title":"Deep anomaly detection on attributed networks","authors":"Ding","year":"2019","venue":"SDM","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ding et al., 2021] Kaize Ding, Qinghai Zhou, Hanghang Tong, and Huan Liu. Few-shot network anomaly detec- tion via cross-network meta-learning. In WWW, 2021.","title":"Few-shot network anomaly detection via cross-network meta-learning","authors":"Ding","year":"2021","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dou et al., 2020] Yingtong Dou, Zhiwei Liu, Li Sun, Yu- tong Deng, Hao Peng, and Philip S. Yu. Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In CIKM, 2020.","title":"Enhancing graph neural network-based fraud detectors against camouflaged fraudsters","authors":"Yingtong Dou, Zhiwei Liu, Li Sun, Yutong Deng, Hao Peng, Philip S Yu","year":"2020","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hamilton et al., 2017] William L. Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In NIPS, 2017.","title":"Inductive representation learning on large graphs","authors":"William L Hamilton, Zhitao Ying, Jure Leskovec","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2021] Mingguo He, Zhewei Wei, Zengfeng Huang, and Hongteng Xu. Bernnet: Learning arbitrary graph spectral filters via bernstein approximation. In NIPS, 2021.","title":"Bernnet: Learning arbitrary graph spectral filters via bernstein approximation","authors":"He","year":"2021","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hu et al., 2020] Wenjie Hu, Yang Yang, Jianbo Wang, Xuanwen Huang, and Ziqiang Cheng. Understanding electricity-theft behavior via multi-source data. In WWW, 2020.","title":"Understanding electricity-theft behavior via multi-source data","authors":"Wenjie Hu, Yang Yang, Jianbo Wang, Xuanwen Huang, Ziqiang Cheng","year":"2020","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jeffreys and Jeffreys, 1999] Harold Jeffreys and Bertha Jef- freys. Methods of Mathematical Physics. Cambridge Mathematical Library. Cambridge University Press, 3 edi- tion, 1999.","title":"Harold Jeffreys and Bertha Jeffreys","authors":"Jeffreys Jeffreys","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kipf and Welling, 2017] Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"Thomas N Kipf, Max Welling","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2019] Ao Li, Zhou Qin, Runshi Liu, Yiqun Yang, and Dong Li. Spam review detection with graph convolu- tional networks. In CIKM, 2019.","title":"Spam review detection with graph convolutional networks","authors":"Ao Li, Zhou Qin, Runshi Liu, Yiqun Yang, Dong Li","year":"2019","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2019] Ziqi Liu, Chaochao Chen, Longfei Li, Jun Zhou, Xiaolong Li, Le Song, and Yuan Qi. Geniepath: Graph neural networks with adaptive receptive paths. In AAAI, 2019.","title":"Geniepath: Graph neural networks with adaptive receptive paths","authors":"Ziqi Liu, Chaochao Chen, Longfei Li, Jun Zhou, Xiaolong Li, Le Song, Yuan Qi","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2020] Zhiwei Liu, Yingtong Dou, Philip S. Yu, Yutong Deng, and Hao Peng. Alleviating the inconsis- tency problem of applying graph neural network to fraud detection. In SIGIR, 2020.","title":"Alleviating the inconsistency problem of applying graph neural network to fraud detection","authors":"Zhiwei Liu, Yingtong Dou, Philip S Yu, Yutong Deng, Hao Peng","year":"2020","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[McPherson et al., 2001] Miller McPherson, Lynn Smith- Lovin, and James M. Cook. Birds of a feather: Homophily in social networks. Review of Sociology, 2001.","title":"Birds of a feather: Homophily in social networks","authors":"Lynn Miller Mcpherson, James M Smith-Lovin, Cook","year":"2001","venue":"Review of Sociology","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Qian et al., 2011] Weikang Qian, Marc D. Riedel, and Ivo G. Rosenberg. Uniform approximation and bernstein polynomials with coefficients in the unit interval. Eur. J. Comb., 2011.","title":"Uniform approximation and bernstein polynomials with coefficients in the unit interval","authors":"Weikang Qian, Marc D Riedel, Ivo G Rosenberg","year":"2011","venue":"Eur. J. Comb","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rayana and Akoglu, 2015] Shebuti Rayana and Leman Akoglu. Collective opinion spam detection: Bridging re- view networks and metadata. In SIGKDD, 2015.","title":"Shebuti Rayana and Leman Akoglu. Collective opinion spam detection: Bridging review networks and metadata","authors":"Akoglu Rayana","year":"2015","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shuman et al., 2013] David I. Shuman, Sunil K. Narang, Pascal Frossard, Antonio Ortega, and Pierre Van- dergheynst. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to net- works and other irregular domains. IEEE Signal Process- ing Magazine, 2013.","title":"The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains","authors":"David I Shuman, K Sunil, Pascal Narang, Antonio Frossard, Pierre Ortega, Vandergheynst","year":"2013","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Veličković et al., 2018] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. In ICLR, 2018.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wang et al., 2019] Daixin Wang, Yuan Qi, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, and Shuang Yang. A semi-supervised graph attentive network for financial fraud detection. In ICDM, 2019.","title":"A semi-supervised graph attentive network for financial fraud detection","authors":"Daixin Wang, Yuan Qi, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, Shuang Yang","year":"2019","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Weber et al., 2019] Mark Weber, Giacomo Domeniconi, Jie Chen, Daniel Karl I. Weidele, Claudio Bellei, Tom Robin- son, and Charles E. Leiserson. Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics. KDD Workshop on Anomaly Detec- tion in Finance, 2019.","title":"Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics","authors":"Mark Weber, Giacomo Domeniconi, Jie Chen, Daniel Karl, I Weidele, Claudio Bellei, Tom Robinson, Charles E Leiserson","year":"2019","venue":"KDD Workshop on Anomaly Detection in Finance","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wu et al., 2019] Felix Wu, Tianyi Zhang, Amauri Holanda de Souza, Christopher Fifty, Tao Yu, and Kilian Q. Wein- berger. Simplifying graph convolutional networks. In ICML, 2019.","title":"Simplifying graph convolutional networks","authors":"Felix Wu, Tianyi Zhang, Amauri Holanda De, Christopher Souza, Tao Fifty, Kilian Q Yu, Weinberger","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xu et al., 2018] Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural net- works. In ICLR, 2018.","title":"How powerful are graph neural networks","authors":"Xu","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xu et al., 2022a] Jiarong Xu, Junru Chen, Yang Yang, Yizhou Sun, Chunping Wang, and Jiangang Lu. Un- supervised adversarially-robust representation learning on graphs. In AAAI, 2022.","title":"Unsupervised adversarially-robust representation learning on graphs","authors":"Xu","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xu et al., 2022b] Jiarong Xu, Yizhou Sun, Xin Jiang, Yan- hao Wang, Yang Yang, Chunping Wang, and Jiangang Lu. Blindfolded attackers still threatening: Strict black-box adversarial attacks on graphs. In AAAI, 2022.","title":"Blindfolded attackers still threatening: Strict black-box adversarial attacks on graphs","authors":"Xu","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yang et al., 2019] Yang Yang, Yuhong Xu, Chunping Wang, Yizhou Sun, Fei Wu, Yueting Zhuang, and Ming Gu. Understanding default behavior in online lending. In CIKM, 2019.","title":"Understanding default behavior in online lending","authors":"Yang Yang, Yuhong Xu, Chunping Wang, Yizhou Sun, Fei Wu, Yueting Zhuang, Ming Gu","year":"2019","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yang et al., 2021] Yang Yang, Yuhong Xu, Yizhou Sun, Yuxiao Dong, Fei Wu, and Yueting Zhuang. Mining fraud- sters and fraudulent strategies in large-scale mobile social networks. IEEE Transactions on Knowledge and Data En- gineering, 2021.","title":"Mining fraudsters and fraudulent strategies in large-scale mobile social networks","authors":"Yang Yang, Yuhong Xu, Yizhou Sun, Yuxiao Dong, Fei Wu, Yueting Zhuang","year":"2021","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}