{"type":"ScholarlyArticle","title":"Robust Heterophilic Graph Learning against Label Noise for Anomaly Detection","authors":[{"name":"Junhang Wu","slug":"junhang-wu","given":"Junhang","family":"Wu","affiliation":"National Engineering Research Center for Multimedia Software , School of Computer Science , Wuhan University; Hubei Key Laboratory of Multimedia and Network Communication Engineering , Wuhan University"},{"name":"Ruimin Hu","slug":"ruimin-hu","given":"Ruimin","family":"Hu","affiliation":"National Engineering Research Center for Multimedia Software , School of Computer Science , Wuhan University; School of Cyber Science and Engineering , Wuhan University"},{"name":"Dengshi Li","slug":"dengshi-li","given":"Dengshi","family":"Li","affiliation":"School of Artificial Intelligence , Jianghan University; National Engineering Research Center for Multimedia Software , School of Computer Science , Wuhan University"},{"name":"Zijun Huang","slug":"zijun-huang","given":"Zijun","family":"Huang","affiliation":"National Engineering Research Center for Multimedia Software , School of Computer Science , Wuhan University; Hubei Key Laboratory of Multimedia and Network Communication Engineering , Wuhan University"},{"name":"Lingfei Ren","slug":"lingfei-ren","given":"Lingfei","family":"Ren","affiliation":"National Engineering Research Center for Multimedia Software , School of Computer Science , Wuhan University; Hubei Key Laboratory of Multimedia and Network Communication Engineering , Wuhan University"},{"name":"Yilong Zang","slug":"yilong-zang","given":"Yilong","family":"Zang","affiliation":"National Engineering Research Center for Multimedia Software , School of Computer Science , Wuhan University; Hubei Key Laboratory of Multimedia and Network Communication Engineering , Wuhan University"}],"abstract":"Given clean labels, Graph Neural Networks (GNNs) have shown promising abilities for graph anomaly detection. However, real-world graphs are inevitably noisy labeled, which drastically degrades the performance of GNNs. To alleviate it, some studies follow the local consistency (a.k.a homophily) assumption to conduct neighborhood-based label noise correction, and to dense raw graphs using raw features or representations learned by poisoned labels. But for the anomaly detection task, the graph is not always homophilic but more likely to be heterophilic, which would corrupt the above assumption due to complicating connection patterns and impairing the effects of message passing. To this end, we propose a novel label noise-resistant graph learning (NRGL) framework, which facilitates robust graph learning from the perspectives of structure augmentation and fine-grained label governance. Specifically, we first present an investigation to verify that increasing graph homophily could help resist label noise. Based on the observation, an unsupervised contrastive learning paradigm is then introduced so well that it cannot only adaptively extract the dual views from the raw graph as structure augmentation, but also enhance the robustness of node representations. Next, given robust node representations, the noisy labels are divided into three candidate sets based on the small-loss criterion for fine-grained noise governance. Furthermore, a node sampler is designed to take structure importance, class frequency, and confidence score into consideration, which helps select reliable and important nodes for training. Extensive experiments on real-world datasets demonstrate the effectiveness of our method.","doi":"10.24963/ijcai.2024/271","url":"https://ijcai.org/proceedings/2024/271","pdf":"https://ijcai.org/proceedings/2024/0271.pdf","markdown":"https://ijcai.org/proceedings/2024/271.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/271","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Data Mining","track":"Main Track","number":271,"pages":{"first":2451,"last":2459},"keywords":["Data Mining: DM: Applications","Data Mining: DM: Mining graphs","Data Mining: DM: Exploratory data mining"],"videos":[],"references":[{"position":1,"raw":"[Arpit et al., 2017] Devansh Arpit, Stanislaw Jastrzebski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, et al. A closer look at memo- rization in deep networks. In Proceedings of International conference on machine learning(ICLR), pages 233-242.","title":"A closer look at memorization in deep networks","authors":"Devansh Arpit, Stanislaw Jastrzebski, Nicolas Ballas, David Krueger, Emmanuel Bengio, S Maxinder, Tegan Kanwal, Asja Maharaj, Aaron Fischer, Yoshua Courville, Bengio","year":null,"venue":"Proceedings of International conference on machine learning(ICLR)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"PMLR, 2017.","title":null,"authors":"Pmlr","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chai et al., 2022] Ziwei Chai, Siqi You, Yang Yang, Shil- iang Pu, Jiarong Xu, Haoyang Cai, and Weihao Jiang. Can abnormality be detected by graph neural networks. In Pro- ceedings of the 29th International Joint Conference on Ar- tificial Intelligence (IJCAI), pages 23-29, 2022.","title":"Can abnormality be detected by graph neural networks","authors":"Ziwei Chai, Siqi You, Yang Yang, Shiliang Pu, Jiarong Xu, Haoyang Cai, Weihao Jiang","year":"2022","venue":"Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2022/270"},{"position":4,"raw":"[Dai et al., 2021] Enyan Dai, Charu Aggarwal, and Suhang Wang. Nrgnn: Learning a label noise resistant graph neu- ral network on sparsely and noisily labeled graphs. In Pro- ceedings of the 27th ACM SIGKDD Conference on Knowl- edge Discovery and Data Mining, pages 227-236, 2021.","title":"Nrgnn: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs","authors":"Dai","year":"2021","venue":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ghosh et al., 2017] Aritra Ghosh, Himanshu Kumar, and P Shanti Sastry. Robust loss functions under label noise for deep neural networks. In Proceedings of the AAAI con- ference on artificial intelligence, pages 1919-1925, 2017.","title":"Robust loss functions under label noise for deep neural networks","authors":"Aritra Ghosh, Himanshu Kumar, Shanti Sastry","year":"2017","venue":"Proceedings of the AAAI conference on artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Goldberger and Ben-Reuven, 2016] Jacob Goldberger and Ehud Ben-Reuven. Training deep neural-networks using a noise adaptation layer. In Proceedings of International conference on learning representations, pages 1-9, 2016.","title":"Training deep neural-networks using a noise adaptation layer","authors":"Ben-Reuven ; Goldberger, Jacob Goldberger, Ehud Ben-Reuven","year":"2016","venue":"Proceedings of International conference on learning representations","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In Proceedings of Advances in neural information processing systems, pages 1024-1034, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"Proceedings of Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Han et al., 2018] Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. Co-teaching: Robust training of deep neural networks with extremely noisy labels. In Proceedings of Advances in neural information processing systems, pages 8536-8546, 2018.","title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","authors":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, Masashi Sugiyama","year":"2018","venue":"Proceedings of Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang et al., 2019] Jinchi Huang, Lie Qu, Rongfei Jia, and Binqiang Zhao. O2u-net: A simple noisy label detection approach for deep neural networks. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3326-3334, 2019.","title":"O2u-net: A simple noisy label detection approach for deep neural networks","authors":"Jinchi Huang, Lie Qu, Rongfei Jia, Binqiang Zhao","year":"2019","venue":"Proceedings of the IEEE/CVF international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jiang et al., 2018] Lu Jiang, Zhengyuan Zhou, Thomas Le- ung, Li-Jia Li, and Li Fei-Fei. Mentornet: Learning data- driven curriculum for very deep neural networks on cor- rupted labels. In Proceedings of International conference on machine learning, pages 2304-2313. PMLR, 2018.","title":"Mentornet: Learning datadriven curriculum for very deep neural networks on corrupted labels","authors":"Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, Li Fei-Fei","year":"2018","venue":"Proceedings of International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jin et al., 2023] Di Jin, Bingdao Feng, Siqi Guo, Xiaobao Wang, Jianguo Wei, and Zhen Wang. Local-global de- fense against unsupervised adversarial attacks on graphs. In Proceedings of the AAAI Conference on Artificial Intel- ligence, pages 8105-8113, 2023.","title":"Local-global defense against unsupervised adversarial attacks on graphs","authors":"Di Jin, Bingdao Feng, Siqi Guo, Xiaobao Wang, Jianguo Wei, Zhen Wang","year":"2023","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kipf and Welling, 2017] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In Proceedings of 5th International Conference on Learning Representations(ICLR), pages 1-14, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2017","venue":"Proceedings of 5th International Conference on Learning Representations(ICLR)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2022] Kuan Li, Yang Liu, Xiang Ao, Jianfeng Chi, Jinghua Feng, Hao Yang, and Qing He. Reliable represen- tations make a stronger defender: Unsupervised structure refinement for robust gnn. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 925-935, 2022.","title":"Reliable representations make a stronger defender: Unsupervised structure refinement for robust gnn","authors":"Kuan Li, Yang Liu, Xiang Ao, Jianfeng Chi, Jinghua Feng, Hao Yang, Qing He","year":"2022","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2024] Xianxian Li, Qiyu Li, Haodong Qian, Jinyan Wang, et al. Contrastive learning of graphs under label noise. Neural Networks, 172:1-12, 2024.","title":"Contrastive learning of graphs under label noise","authors":"Li","year":"2024","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2021] Yang Liu, Xiang Ao, Zidi Qin, Jianfeng Chi, Jinghua Feng, Hao Yang, and Qing He. Pick and choose: a gnn-based imbalanced learning approach for fraud detection. In Proceedings of International World Wide Web Conferences, pages 3168-3177, 2021.","title":"Pick and choose: a gnn-based imbalanced learning approach for fraud detection","authors":"Yang Liu, Xiang Ao, Zidi Qin, Jianfeng Chi, Jinghua Feng, Hao Yang, Qing He","year":"2021","venue":"Proceedings of International World Wide Web Conferences","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[NT et al., 2019] Hoang NT, Choong Jun Jin, and Tsuyoshi Murata. Learning graph neural networks with noisy labels. arXiv preprint arXiv:1905.01591, pages 1-5, 2019.","title":"Learning graph neural networks with noisy labels","authors":"N T Hoang, Choong Jun, Jin, Tsuyoshi Murata","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Patrini et al., 2017] Giorgio Patrini, Alessandro Rozza, Aditya Krishna Menon, Richard Nock, and Lizhen Qu. Making deep neural networks robust to label noise: A loss correction approach. In Proceedings of the IEEE confer- ence on computer vision and pattern recognition, pages 1944-1952, 2017.","title":"Making deep neural networks robust to label noise: A loss correction approach","authors":"Giorgio Patrini, Alessandro Rozza, Aditya Krishna Menon, Richard Nock, Lizhen Qu","year":"2017","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Qian et al., 2023] Siyi Qian, Haochao Ying, Renjun Hu, Jingbo Zhou, Jintai Chen, Danny Z Chen, and Jian Wu. Robust training of graph neural networks via noise gover- nance. In Proceedings of the 16th ACM International Con- ference on Web Search and Data Mining (WSDM), pages 607-615, 2023.","title":"Robust training of graph neural networks via noise governance","authors":"Haochao Siyi Qian, Renjun Ying, Jingbo Hu, Jintai Zhou, Danny Z Chen, Jian Chen, Wu","year":"2023","venue":"Proceedings of the 16th ACM International Conference on Web Search and Data Mining (WSDM)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rayana and Akoglu, 2015] Shebuti Rayana and Leman Akoglu. Collective opinion spam detection: Bridging re- view networks and metadata. In Proceedings of the 21th ACM SIGKDD International CSonference on Knowledge Discovery and Data Mining, pages 985-994, 2015.","title":"Shebuti Rayana and Leman Akoglu. Collective opinion spam detection: Bridging review networks and metadata","authors":"Akoglu Rayana","year":"2015","venue":"Proceedings of the 21th ACM SIGKDD International CSonference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tang et al., 2022] Jianheng Tang, Jiajin Li, Ziqi Gao, and Jia Li. Rethinking graph neural networks for anomaly de- tection. In Proceedings of International Conference on Machine Learning, pages 21076-21089. PMLR, 2022.","title":"Rethinking graph neural networks for anomaly detection","authors":"Tang","year":"2022","venue":"Proceedings of International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2019] Yisen Wang, Xingjun Ma, Zaiyi Chen, Yuan Luo, Jinfeng Yi, and James Bailey. Symmetric cross entropy for robust learning with noisy labels. In Proceed- ings of the IEEE/CVF international conference on com- puter vision, pages 322-330, 2019.","title":"Symmetric cross entropy for robust learning with noisy labels","authors":"Wang","year":"2019","venue":"Proceedings of the IEEE/CVF international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Weber et al., 2019] Mark Weber, Giacomo Domeniconi, Jie Chen, Daniel Karl I Weidele, Claudio Bellei, Tom Robin- son, and Charles Leiserson. Anti-money laundering in bit- coin: Experimenting with graph convolutional networks for financial forensics. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining in Finance Workshop, pages 1-7, 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 Leiserson","year":"2019","venue":"ACM SIGKDD International Conference on Knowledge Discovery and Data Mining in Finance Workshop","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2022] Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, and Bin Cui. Graph neural networks in rec- ommender systems: a survey. ACM Computing Surveys, 55(5):1-37, 2022.","title":"Graph neural networks in recommender systems: a survey","authors":"Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, Bin Cui","year":"2022","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yu et al., 2019] Xingrui Yu, Bo Han, Jiangchao Yao, Gang Niu, Ivor Tsang, and Masashi Sugiyama. How does dis- agreement help generalization against label corruption? In Proceedings of International Conference on Machine Learning, pages 7164-7173. PMLR, 2019.","title":"How does disagreement help generalization against label corruption?","authors":"Yu","year":"2019","venue":"Proceedings of International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yuan et al., 2023] Jingyang Yuan, Xiao Luo, Yifang Qin, Yusheng Zhao, Wei Ju, and Ming Zhang. Learning on graphs under label noise. In Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1-5. IEEE, 2023.","title":"Learning on graphs under label noise","authors":"Jingyang Yuan, Xiao Luo, Yifang Qin, Yusheng Zhao, Wei Ju, Ming Zhang","year":"2023","venue":"Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP)","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang and Sabuncu, 2018] Zhilu Zhang and Mert Sabuncu. Generalized cross entropy loss for training deep neural networks with noisy labels. In Proceedings of Advances in neural information processing systems, pages 8792-8802, 2018.","title":"Generalized cross entropy loss for training deep neural networks with noisy labels","authors":"Sabuncu Zhang, Zhilu Zhang, Mert Sabuncu","year":"2018","venue":"Proceedings of Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2021] Ge Zhang, Jia Wu, Jian Yang, Amin Beheshti, Shan Xue, Chuan Zhou, and Quan Z Sheng. Fraudre: Fraud detection dual-resistant to graph inconsis- tency and imbalance. In Proceedings of International Con- ference on Data Mining (ICDM), pages 867-876. IEEE, 2021.","title":"Fraudre: Fraud detection dual-resistant to graph inconsistency and imbalance","authors":"Ge Zhang, Jia Wu, Jian Yang, Amin Beheshti, Shan Xue, Chuan Zhou, Quan, Sheng","year":"2021","venue":"Proceedings of International Conference on Data Mining (ICDM)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhao et al., 2023] Ruoyan Zhao, Zhou Shao, Wenhu Zhang, Jiachen Zhang, and Chunming Wu. A multi-channel multi- tower gnn model for job transfer prediction based on aca- demic social network. Applied Soft Computing, 142:1-10, 2023.","title":"A multi-channel multitower gnn model for job transfer prediction based on academic social network","authors":"Zhao","year":"2023","venue":"Applied Soft Computing","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zheng et al., 2023] Wen Zheng, Bingbing Xu, Emiao Lu, Yang Li, Qi Cao, Xuan Zong, and Huawei Shen. Midlg: Mutual information based dual level gnn for transaction fraud complaint verification. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5685-5694, 2023.","title":"Midlg: Mutual information based dual level gnn for transaction fraud complaint verification","authors":"Wen Zheng, Bingbing Xu, Emiao Lu, Yang Li, Qi Cao, Xuan Zong, Huawei Shen","year":"2023","venue":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhu et al., 2020] Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. Be- yond homophily in graph neural networks: Current limita- tions and effective designs. In Proceedings of Advances in neural information processing systems, pages 7793-7804, 2020.","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","authors":"Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, Danai Koutra","year":"2020","venue":"Proceedings of Advances in neural information processing systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}