On Anomaly Interpretation via Shapley Values

Anomaly localization is an essential problem as anomaly detection is. Because a rigorous localization requires a causal model of a target system, practically we often resort to a relaxed problem of anomaly interpretation, for which we are to obtain meaningful attribution of anomaly scores to input features. In this paper, we investigate the use of the Shapley value for anomaly interpretation. We focus on the semi-supervised anomaly detection and newly propose a characteristic function, on which the Shapley value is computed, specifically for anomaly scores. The idea of the proposed method is approximating the absence of some features by minimizing an anomaly score with regard to them. We examine the performance of the proposed method as well as other general approaches to computing the Shapley value in interpreting anomaly scores. We show the results of experiments on multiple datasets and anomaly detection methods, which indicate the usefulness of the Shapley-based anomaly interpretation toward anomaly localization.

[1]  Ambuj K. Singh,et al.  Outlier Detection from Network Data with Subnetwork Interpretation , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[2]  A. Charnes,et al.  Extremal Principle Solutions of Games in Characteristic Function Form: Core, Chebychev and Shapley Value Generalizations , 1988 .

[3]  L. Shapley.  A Value for n-person Games , 1988 .

[4]  Shigeki Takeuchi,et al.  Consistent and Efficient Nonparametric Different-Feature Selection , 2017, AISTATS.

[5]  Markus H. Gross,et al.  Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation , 2019, ICML.

[6]  Donghwa Shin,et al.  Contextual Outlier Interpretation , 2017, IJCAI.

[7]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[8]  Mukund Sundararajan,et al.  The many Shapley values for model explanation , 2019, ICML.

[9]  Ali A. Ghorbani,et al.  A detailed analysis of the KDD CUP 99 data set , 2009, 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications.

[10]  Hans-Peter Kriegel,et al.  Outlier Detection in Arbitrarily Oriented Subspaces , 2012, 2012 IEEE 12th International Conference on Data Mining.

[11]  Erik Strumbelj,et al.  Explaining prediction models and individual predictions with feature contributions , 2014, Knowledge and Information Systems.

[12]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[13]  Manish Marwah,et al.  ACE – An Anomaly Contribution Explainer for Cyber-Security Applications , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[14]  Ioana Giurgiu,et al.  Additive Explanations for Anomalies Detected from Multivariate Temporal Data , 2019, CIKM.

[15]  Kjersti Aas,et al.  Explaining individual predictions when features are dependent: More accurate approximations to Shapley values , 2019, Artif. Intell..

[16]  Bo Zong,et al.  Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection , 2018, ICLR.

[17]  Art B. Owen,et al.  On Shapley Value for Measuring Importance of Dependent Inputs , 2016, SIAM/ASA J. Uncertain. Quantification.

[18]  Naoya Takeishi.  Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detection , 2019, 2019 International Conference on Data Mining Workshops (ICDMW).

[19]  Lior Rokach,et al.  Explaining Anomalies Detected by Autoencoders Using SHAP , 2019, ArXiv.

[20]  Ankur Taly,et al.  Axiomatic Attribution for Deep Networks , 2017, ICML.

[21]  Yair Zick,et al.  Algorithmic Transparency via Quantitative Input Influence , 2017 .

[22]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[23]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[24]  Klemens Böhm,et al.  HiCS: High Contrast Subspaces for Density-Based Outlier Ranking , 2012, 2012 IEEE 28th International Conference on Data Engineering.

[25]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[26]  Thomas G. Dietterich,et al.  Sequential Feature Explanations for Anomaly Detection , 2019, ACM Trans. Knowl. Discov. Data.

[27]  James Bailey,et al.  Scalable Outlying-Inlying Aspects Discovery via Feature Ranking , 2015, PAKDD.

[28]  Daniel Gómez,et al.  Improving polynomial estimation of the Shapley value by stratified random sampling with optimum allocation , 2017, Comput. Oper. Res..

[29]  Martin Kopp,et al.  Anomaly explanation with random forests , 2020, Expert Syst. Appl..

[30]  S. Lipovetsky.  Entropy Criterion In Logistic Regression And Shapley Value Of Predictors , 2006 .