ABSTRACT
Most existing deep learning models are trained based on the closed-world assumption, where the test data is assumed to be drawn i.i.d. from the same distribution as the training data, known as in-distribution (ID). However, when models are deployed in an open-world scenario, test samples can be out-of-distribution (OOD) and therefore should be handled with caution. To detect such OOD samples drawn from unknown distribution, OOD detection has received increasing attention lately. However, current endeavors mostly focus on grid-structured data and its application for graph-structured data remains under-explored. Considering the fact that data labeling on graphs is commonly time-expensive and labor-intensive, in this work we study the problem of unsupervised graph OOD detection, aiming at detecting OOD graphs solely based on unlabeled ID data. To achieve this goal, we develop a new graph contrastive learning framework GOOD-D for detecting OOD graphs without using any ground-truth labels. By performing hierarchical contrastive learning on the augmented graphs generated by our perturbation-free graph data augmentation method, GOOD-D is able to capture the latent ID patterns and accurately detect OOD graphs based on the semantic inconsistency in different granularities (i.e., node-level, graph-level, and group-level). As a pioneering work in unsupervised graph-level OOD detection, we build a comprehensive benchmark to compare our proposed approach with different state-of-the-art methods. The experiment results demonstrate the superiority of our approach over different methods on various datasets.
Supplemental Material
- Yunsheng Bai, Hao Ding, Song Bian, Ting Chen, Yizhou Sun, and Wei Wang. 2019. Simgnn: A neural network approach to fast graph similarity computation. In WSDM. 384--392.Google ScholarDigital Library
- Markus M Breunig, Hans-Peter Kriegel, Raymond T Ng, and Jörg Sander. 2000. LOF: identifying density-based local outliers. In SIGMOD. 93--104.Google Scholar
- Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In ICML. PMLR, 1597--1607.Google Scholar
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NeurIPS.Google Scholar
- Kaize Ding, Jundong Li, Nitin Agarwal, and Huan Liu. 2021. Inductive anomaly detection on attributed networks. In IJCAI.Google Scholar
- Kaize Ding, Jundong Li, Rohit Bhanushali, and Huan Liu. 2019. Deep anomaly detection on attributed networks. In SDM. SIAM, 594--602.Google Scholar
- Kaize Ding, Yancheng Wang, Yingzhen Yang, and Huan Liu. 2022a. Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive Learning. arXiv preprint arXiv:2202.08480 (2022).Google Scholar
- Kaize Ding, Zhe Xu, Hanghang Tong, and Huan Liu. 2022b. Data augmentation for deep graph learning: A survey. arXiv preprint arXiv:2202.08235 (2022).Google Scholar
- Vijay Prakash Dwivedi, Chaitanya K Joshi, Thomas Laurent, Yoshua Bengio, and Xavier Bresson. 2020. Benchmarking graph neural networks. arXiv preprint arXiv:2003.00982 (2020).Google Scholar
- Vijay Prakash Dwivedi, Anh Tuan Luu, Thomas Laurent, Yoshua Bengio, and Xavier Bresson. 2022. Graph Neural Networks with Learnable Structural and Positional Representations. In ICLR.Google Scholar
- Shaohua Fan, Xiao Wang, Chuan Shi, Peng Cui, and Bai Wang. 2021. Generalizing Graph Neural Networks on Out-Of-Distribution Graphs. arXiv preprint arXiv:2111.10657 (2021).Google Scholar
- Izhak Golan and Ran El-Yaniv. 2018. Deep anomaly detection using geometric transformations. In NeurIPS.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NeurIPS, Vol. 30.Google Scholar
- Kaveh Hassani and Amir Hosein Khasahmadi. 2020. Contrastive multi-view representation learning on graphs. In ICML. PMLR, 4116--4126.Google Scholar
- Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In CVPR.Google Scholar
- Dan Hendrycks and Kevin Gimpel. 2017. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. In ICLR.Google Scholar
- Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. In NeurIPS, Vol. 33. 22118--22133.Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.Google Scholar
- Haoyang Li, Xin Wang, Ziwei Zhang, and Wenwu Zhu. 2022. Out-of-distribution generalization on graphs: A survey. arXiv preprint arXiv:2202.07987 (2022).Google Scholar
- Junnan Li, Pan Zhou, Caiming Xiong, and Steven Hoi. 2021. Prototypical Contrastive Learning of Unsupervised Representations. In ICLR.Google Scholar
- Qingbiao Li, Fernando Gama, Alejandro Ribeiro, and Amanda Prorok. 2020. Graph neural networks for decentralized multi-robot path planning. In IROS.Google Scholar
- Shiyu Liang, Yixuan Li, and R Srikant. 2018. Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks. In ICLR.Google Scholar
- Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. 2008. Isolation forest. In ICDM.Google ScholarDigital Library
- Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, and Jie Tang. 2021b. Self-supervised learning: Generative or contrastive. TKDE (2021).Google Scholar
- Yixin Liu, Ming Jin, Shirui Pan, Chuan Zhou, Yu Zheng, Feng Xia, and Philip Yu. 2022a. Graph self-supervised learning: A survey. TKDE (2022).Google Scholar
- Yixin Liu, Zhao Li, Shirui Pan, Chen Gong, Chuan Zhou, and George Karypis. 2021a. Anomaly detection on attributed networks via contrastive self-supervised learning. TNNLS (2021).Google Scholar
- Yixin Liu, Yu Zheng, Daokun Zhang, Hongxu Chen, Hao Peng, and Shirui Pan. 2022b. Towards unsupervised deep graph structure learning. In WWW.Google Scholar
- Xuexiong Luo, Jia Wu, Amin Beheshti, Jian Yang, Xiankun Zhang, Yuan Wang, and Shan Xue. 2022. ComGA: Community-Aware Attributed Graph Anomaly Detection. In WSDM. 657--665.Google Scholar
- Rongrong Ma, Guansong Pang, Ling Chen, and Anton van den Hengel. 2022. Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation. In WSDM.Google Scholar
- Larry M Manevitz and Malik Yousef. 2001. One-class SVMs for document classification. JMLR, Vol. 2, Dec (2001), 139--154.Google Scholar
- Christopher Morris, Nils M. Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and Marion Neumann. 2020. TUDataset: A collection of benchmark datasets for learning with graphs. In ICML Workshop.Google Scholar
- Marion Neumann, Roman Garnett, Christian Bauckhage, and Kristian Kersting. 2016. Propagation kernels: efficient graph kernels from propagated information. Machine Learning, Vol. 102, 2 (2016), 209--245.Google ScholarDigital Library
- Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, and Jie Tang. 2020. GCC: Graph contrastive coding for graph neural network pre-training. In SIGKDD. 1150--1160.Google ScholarDigital Library
- Jie Ren, Peter J Liu, Emily Fertig, Jasper Snoek, Ryan Poplin, Mark Depristo, Joshua Dillon, and Balaji Lakshminarayanan. 2019. Likelihood ratios for out-of-distribution detection. In NeurIPS, Vol. 32.Google Scholar
- Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexander Binder, Emmanuel Müller, and Marius Kloft. 2018. Deep one-class classification. In ICML. PMLR, 4393--4402.Google Scholar
- Marco Schreyer, Timur Sattarov, Damian Borth, Andreas Dengel, and Bernd Reimer. 2017. Detection of anomalies in large scale accounting data using deep autoencoder networks. arXiv preprint arXiv:1709.05254 (2017).Google Scholar
- Vikash Sehwag, Mung Chiang, and Prateek Mittal. 2021. SSD: A Unified Framework for Self-Supervised Outlier Detection. In ICLR.Google Scholar
- Nino Shervashidze, Pascal Schweitzer, Erik Jan Van Leeuwen, Kurt Mehlhorn, and Karsten M Borgwardt. 2011. Weisfeiler-lehman graph kernels. JMLR, Vol. 12, 9 (2011).Google ScholarDigital Library
- Maximilian Stadler, Bertrand Charpentier, Simon Geisler, Daniel Zügner, and Stephan Günnemann. 2021. Graph posterior network: Bayesian predictive uncertainty for node classification. In NeruIPS, Vol. 34. 18033--18048.Google Scholar
- Fan-Yun Sun, Jordon Hoffman, Vikas Verma, and Jian Tang. 2020. InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization. In ICLR.Google Scholar
- Yue Tan, Guodong Long, Lu Liu, Tianyi Zhou, Qinghua Lu, Jing Jiang, and Chengqi Zhang. 2022a. Fedproto: Federated prototype learning across heterogeneous clients. In AAAI, Vol. 1. 3.Google Scholar
- Yue Tan, Guodong Long, Jie Ma, Lu Liu, Tianyi Zhou, and Jing Jiang. 2022b. Federated Learning from Pre-Trained Models: A Contrastive Learning Approach. In NeurIPS.Google Scholar
- Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. JMLR, Vol. 9, 11 (2008).Google Scholar
- Petar Velickovic, William Fedus, William L Hamilton, Pietro Liò, Yoshua Bengio, and R Devon Hjelm. 2020. Deep Graph Infomax.. In ICLR.Google Scholar
- Petar Veli?kovi?, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In ICLR.Google Scholar
- S Vichy N Vishwanathan, Nicol N Schraudolph, Risi Kondor, and Karsten M Borgwardt. 2010. Graph kernels. JMLR, Vol. 11 (2010), 1201--1242.Google ScholarDigital Library
- Yingheng Wang, Yaosen Min, Xin Chen, and Ji Wu. 2021. Multi-view graph contrastive representation learning for drug-drug interaction prediction. In WWW.Google Scholar
- Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In ICML. PMLR.Google Scholar
- Zhi-Fan Wu, Tong Wei, Jianwen Jiang, Chaojie Mao, Mingqian Tang, and Yu-Feng Li. 2021. NGC: a unified framework for learning with open-world noisy data. In CVPR. 62--71.Google Scholar
- Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In ICLR.Google Scholar
- Jiaxuan You, Rex Ying, and Jure Leskovec. 2019. Position-aware graph neural networks. In ICML. PMLR, 7134--7143.Google Scholar
- Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. In NeurIPS, Vol. 33. 5812--5823.Google Scholar
- Junliang Yu, Hongzhi Yin, Jundong Li, Qinyong Wang, Nguyen Quoc Viet Hung, and Xiangliang Zhang. 2021. Self-supervised multi-channel hypergraph convolutional network for social recommendation. In WWW. 413--424.Google Scholar
- Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor Prasanna. 2020. GraphSAINT: Graph Sampling Based Inductive Learning Method. In ICLR.Google Scholar
- He Zhang, Bang Wu, Xingliang Yuan, Shirui Pan, Hanghang Tong, and Jian Pei. 2022. Trustworthy Graph Neural Networks: Aspects, Methods and Trends. arXiv preprint arXiv:2205.07424 (2022).Google Scholar
- Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. In NeurIPS, Vol. 31.Google Scholar
- Lingxiao Zhao and Leman Akoglu. 2021. On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights. Big Data (2021).Google Scholar
- Xujiang Zhao, Feng Chen, Shu Hu, and Jin-Hee Cho. 2020. Uncertainty aware semi-supervised learning on graph data. In NeurIPS, Vol. 33. 12827--12836.Google Scholar
- Xin Zheng, Miao Zhang, Chunyang Chen, Chaojie Li, Chuan Zhou, and Shirui Pan. 2022b. Multi-Relational Graph Neural Architecture Search with Fine-grained Message Passing. In ICDM.Google Scholar
- Yizhen Zheng, Shirui Pan, Vincent Cs Lee, Yu Zheng, and Philip S Yu. 2022a. Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination. In NeurIPS.Google Scholar
- Yizhen Zheng, Yu Zheng, Xiaofei Zhou, Chen Gong, Vincent Lee, and Shirui Pan. 2022c. Unifying Graph Contrastive Learning with Flexible Contextual Scopes. In ICDM.Google Scholar
- Wenxuan Zhou, Fangyu Liu, and Muhao Chen. 2021. Contrastive Out-of-Distribution Detection for Pretrained Transformers. In EMNLP. 1100--1111.Google Scholar
- Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, and Liang Wang. 2021. Graph contrastive learning with adaptive augmentation. In WWW. 2069--2080.Google Scholar
Index Terms
- GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection
Recommendations
Towards Unsupervised Deep Graph Structure Learning
WWW '22: Proceedings of the ACM Web Conference 2022In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated when noisy connections occur in the original graph structures; besides, the ...
A Data-centric Framework to Endow Graph Neural Networks with Out-Of-Distribution Detection Ability
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningOut-of-distribution (OOD) detection, which aims to identify OOD samples from in-distribution (ID) ones in test time, has become an essential problem in machine learning. However, existing works are mostly conducted on Euclidean data, and the problem in ...
Class Label-aware Graph Anomaly Detection
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementUnsupervised GAD methods assume the lack of anomaly labels, i.e., whether a node is anomalous or not. One common observation we made from previous unsupervised methods is that they not only assume the absence of such anomaly labels, but also the absence ...
Comments