Guansong Pang
Charu Aggarwal
ABSTRACT
Anomaly explanation, also known as anomaly localization, is as important as, if not more than, anomaly detection in many real-world applications. However, it is challenging to build explainable detection models due to the lack of anomaly-supervisory information and the unbounded nature of anomaly; most existing studies exclusively focus on the detection task only, including the recently emerging deep learning-based anomaly detection that leverages neural networks to learn expressive low-dimensional representations or anomaly scores for the detection task. Deep learning models, including deep anomaly detection models, are often constructed as black boxes, which have been criticized for the lack of explainability of their prediction results. To tackle this explainability issue, there have been numerous techniques introduced over the years, many of which can be utilized or adapted to offer highly explainable detection results.
This tutorial aims to present a comprehensive review of the advances in deep learning-based anomaly detection and explanation. We first review popular state-of-the-art deep anomaly detection methods from different categories of approaches, followed by the introduction of a number of principled approaches used to provide anomaly explanation for deep detection models. Through this tutorial, we aim to promote the development in algorithms, theories and evaluation of explainable deep anomaly detection in the machine learning and data mining community. The slides and other materials of the tutorial are made publicly available at https://tinyurl.com/explainableDeepAD.
- Charu C Aggarwal. 2017. Outlier analysis .Springer.Google Scholar
- Fabrizio Angiulli, Fabio Fassetti, Giuseppe Manco, and Luigi Palopoli. 2017a. Outlying property detection with numerical attributes. Data Mining and Knowledge Discovery , Vol. 31, 1 (2017), 134--163.Google ScholarDigital Library
- Fabrizio Angiulli, Fabio Fassetti, Giuseppe Manco, and Luigi Palopoli. 2017b. Outlying property detection with numerical attributes. Data mining and knowledge discovery , Vol. 31, 1 (2017), 134--163.Google Scholar
- Fabrizio Angiulli, Fabio Fassetti, and Luigi Palopoli. 2009. Detecting outlying properties of exceptional objects. ACM Transactions on Database Systems , Vol. 34, 1 (2009), 1--62.Google ScholarDigital Library
- Fatemeh Azmandian, Jennifer G Dy, Javed A Aslam, and David R Kaeli. 2012. Local kernel density ratio-based feature selection for outlier detection. In Asian Conference on Machine Learning. PMLR, 49--64.Google Scholar
- Fatemeh Azmandian, Ayse Yilmazer, Jennifer G Dy, Javed A Aslam, and David R Kaeli. 2014. Harnessing the power of GPUs to speed up feature selection for outlier detection. Journal of Computer Science and Technology , Vol. 29, 3 (2014), 408--422.Google ScholarCross Ref
- Paul Bergmann, Sindy Löwe, Michael Fauser, David Sattlegger, and Carsten Steger. 2018. Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv preprint arXiv:1807.02011 (2018).Google Scholar
- Jinghui Chen, Saket Sathe, Charu Aggarwal, and Deepak Turaga. 2017. Outlier detection with autoencoder ensembles. In SDM. 90--98.Google Scholar
- Yuanhong Chen, Yu Tian, Guansong Pang, and Gustavo Carneiro. 2021. Unsupervised Anomaly Detection and Localisation with Multi-scale Interpolated Gaussian Descriptors. arXiv preprint arXiv:2101.10043 .Google Scholar
- Mengnan Du, Ninghao Liu, and Xia Hu. 2019. Techniques for interpretable machine learning. Commun. ACM , Vol. 63, 1 (2019), 68--77.Google ScholarDigital Library
- Lei Duan, Guanting Tang, Jian Pei, James Bailey, Akiko Campbell, and Changjie Tang. 2015. Mining outlying aspects on numeric data. Data Mining and Knowledge Discovery , Vol. 29, 5 (2015), 1116--1151.Google ScholarDigital Library
- Nikhil Gupta, Dhivya Eswaran, Neil Shah, Leman Akoglu, and Christos Faloutsos. 2018. Beyond outlier detection: Lookout for pictorial explanation. In ECMLPKDD. Springer, 122--138.Google Scholar
- Radu Tudor Ionescu, Fahad Shahbaz Khan, Mariana-Iuliana Georgescu, and Ling Shao. 2019. Object-centric auto-encoders and dummy anomalies for abnormal event detection in video. In CVPR . 7842--7851.Google Scholar
- Radu Tudor Ionescu, Sorina Smeureanu, Bogdan Alexe, and Marius Popescu. 2017. Unmasking the abnormal events in video. In ICCV. 2895--2903.Google Scholar
- Aleksandar Lazarevic and Vipin Kumar. 2005. Feature bagging for outlier detection. In KDD. 157--166.Google Scholar
- Haoyu Liu, Fenglong Ma, Yaqing Wang, Shibo He, Jiming Chen, and Jing Gao. 2020. LP-Explain: Local Pictorial Explanation for Outliers. In ICDM. IEEE, 372--381.Google Scholar
- Philipp Liznerski, Lukas Ruff, Robert A Vandermeulen, Billy Joe Franks, Marius Kloft, and Klaus-Robert Müller. 2021. Explainable deep one-class classification. In ICLR .Google Scholar
- Weixin Luo, Zaiwang Gu, Jiang Liu, and Shenghua Gao. 2020. Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images. In ECCV . Springer.Google Scholar
- W James Murdoch, Chandan Singh, Karl Kumbier, Reza Abbasi-Asl, and Bin Yu. 2019. Definitions, methods, and applications in interpretable machine learning. Proceedings of the National Academy of Sciences , Vol. 116, 44 (2019), 22071--22080.Google ScholarCross Ref
- Guansong Pang, Longbing Cao, Ling Chen, Defu Lian, and Huan Liu. 2018b. Sparse modeling-based sequential ensemble learning for effective outlier detection in high-dimensional numeric data. In AAAI. 3892--3899.Google Scholar
- Guansong Pang, Longbing Cao, Ling Chen, and Huan Liu. 2016. Unsupervised feature selection for outlier detection by modelling hierarchical value-feature couplings. In ICDM. IEEE, 410--419.Google Scholar
- Guansong Pang, Longbing Cao, Ling Chen, and Huan Liu. 2017. Learning homophily couplings from non-IID data for joint feature selection and noise-resilient outlier detection. In IJCAI. 2585--2591.Google Scholar
- Guansong Pang, Longbing Cao, Ling Chen, and Huan Liu. 2018a. Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection. In KDD. 2041--2050.Google Scholar
- Guansong Pang, Chunhua Shen, Longbing Cao, and Anton Van Den Hengel. 2021. Deep Learning for Anomaly Detection: A Review. ACM Computing Surveys (CSUR) , Vol. 54, 2 (2021), 1--38.Google ScholarDigital Library
- Guansong Pang, Chunhua Shen, Huidong Jin, and Anton van den Hengel. 2019 b. Deep Weakly-supervised Anomaly Detection. arXiv preprint:1910.13601 (2019).Google Scholar
- Guansong Pang, Chunhua Shen, and Anton van den Hengel. 2019 a. Deep Anomaly Detection with Deviation Networks. In KDD. 353--362.Google Scholar
- Guansong Pang, Cheng Yan, Chunhua Shen, Anton van den Hengel, and Xiao Bai. 2020. Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection. In CVPR . 12173--12182.Google Scholar
- Lukas Ruff, Nico Görnitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Robert Vandermeulen, Alexander Binder, Emmanuel Müller, and Marius Kloft. 2018. Deep one-class classification. In ICML. 4390--4399.Google Scholar
- Lukas Ruff, Robert A Vandermeulen, Nico Görnitz, Alexander Binder, Emmanuel Müller, Klaus-Robert Müller, and Marius Kloft. 2020. Deep semi-supervised anomaly detection. ICLR .Google Scholar
- Mohammad Sabokrou, Mohammad Khalooei, Mahmood Fathy, and Ehsan Adeli. 2018. Adversarially learned one-class classifier for novelty detection. In CVPR . 3379--3388.Google Scholar
- Mohammadreza Salehi, Niousha Sadjadi, Soroosh Baselizadeh, Mohammad H. Rohban, and Hamid R. Rabiee. 2021. Multiresolution Knowledge Distillation for Anomaly Detection. In CVPR . 14902--14912.Google Scholar
- Waqas Sultani, Chen Chen, and Mubarak Shah. 2018. Real-world anomaly detection in surveillance videos. In CVPR. 6479--6488.Google Scholar
- Yu Tian, Guansong Pang, Yuanhong Chen, Rajvinder Singh, Johan W Verjans, and Gustavo Carneiro. 2021. Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning. arXiv preprint arXiv:2101.10030 (2021).Google Scholar
- Shashanka Venkataramanan, Kuan-Chuan Peng, Rajat Vikram Singh, and Abhijit Mahalanobis. 2020. Attention Guided Anomaly Localization in Images. In ECCV. Springer, 485--503.Google Scholar
- Nguyen Xuan Vinh, Jeffrey Chan, Simone Romano, James Bailey, Christopher Leckie, Kotagiri Ramamohanarao, and Jian Pei. 2016. Discovering outlying aspects in large datasets. Data Mining and Knowledge Discovery , Vol. 30, 6 (2016), 1520--1555.Google ScholarDigital Library
- Hu Wang, Guansong Pang, Chunhua Shen, and Congbo Ma. 2020. Unsupervised Representation Learning by Predicting Random Distances. In IJCAI .Google Scholar
- Yue Wu, Leman Akoglu, and Ian Davidson. 2019. Coverage-based Outlier Explanation. arXiv preprint arXiv:1911.02617 (2019).Google Scholar
- Hongzuo Xu, Yijie Wang, Songlei Jian, Zhenyu Huang, Yongjun Wang, Ning Liu, and Fei Li. 2021. Beyond Outlier Detection: Outlier Interpretation by Attention-Guided Triplet Deviation Network. In Web Conference. 1328--1339.Google ScholarDigital Library
- Panpan Zheng, Shuhan Yuan, Xintao Wu, Jun Li, and Aidong Lu. 2019. One-class adversarial nets for fraud detection. In AAAI. 1286--1293.Google Scholar
- Chong Zhou and Randy C Paffenroth. 2017. Anomaly detection with robust deep autoencoders. In KDD. ACM, 665--674.Google Scholar
- Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Daeki Cho, and Haifeng Chen. 2018. Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In ICLR .Google Scholar
Index Terms
- Toward Explainable Deep Anomaly Detection
Recommendations
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningWe consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the ...
Deep Anomaly Detection with Deviation Networks
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningAlthough deep learning has been applied to successfully address many data mining problems, relatively limited work has been done on deep learning for anomaly detection. Existing deep anomaly detection methods, which focus on learning new feature ...
A Survey on Explainable Anomaly Detection
In the past two decades, most research on anomaly detection has focused on improving the accuracy of the detection, while largely ignoring the explainability of the corresponding methods and thus leaving the explanation of outcomes to practitioners. As ...
Comments