Abstract
The need for explainable AI (XAI) is well established but relatively little has been published outside of the supervised learning paradigm. This paper focuses on a principled approach to applying explainability and interpretability to the task of unsupervised anomaly detection. We argue that explainability is principally an algorithmic task and interpretability is principally a cognitive task, and draw on insights from the cognitive sciences to propose a general-purpose method for practical diagnosis using explained anomalies. We define Attribution Error, and demonstrate, using real-world labeled datasets, that our method based on Integrated Gradients (IG) yields significantly lower attribution errors than alternative methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Proportionality in this work is different from Proportionality defined in [35], since Proportionality in the latter refers to a condition under which the dimensional components of the distance between a baseline point and an observation is proportional to the attribution.
- 2.
We apply equal weighting to each relevant dimension in \(\beta (x)\), because our technician labelers have found it impractical to assign relative importance weights/preference to the relevant dimensions.
References
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (xai). IEEE Access 6, 52138–52160 (2018)
Aggarwal, C.C.: Outlier Analysis, 2nd edn. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-47578-3
Antwarg, L., Miller, R.M., Shapira, B., Rokach, L.: Explaining anomalies detected by autoencoders using shap (2020)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), 1–46 (2015)
Binder, A., Montavon, G., Lapuschkin, S., Müller, K.-R., Samek, W.: Layer-wise relevance propagation for neural networks with local renormalization layers. In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9887, pp. 63–71. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44781-0_8
Broniatowski, D.: Psychological foundations of explainability and interpretability in artificial intelligence (2021–04-12 04:04:00 2021)
Carletti, M., Terzi, M., Susto, G.A.: Interpretable anomaly detection with diffi: Depth-based isolation forest feature importance (2020)
Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41(3) (2009). https://doi.org/10.1145/1541880.1541882
Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning (2017)
Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M.A., Kagal, L.: Explaining explanations: an approach to evaluating interpretability of machine learning. CoRR abs/1806.00069 (2018)
Kauffmann, J., Müller, K.R., Montavon, G.: Towards explaining anomalies: a deep Taylor decomposition of one-class models. Pattern Recogn. 101, 107198 (2020). https://doi.org/10.1016/j.patcog.2020.107198
Lieto, A., Radicioni, D.P., Rho, V.: Dual PECCS: a cognitive system for conceptual representation and categorization. J. Exp. Theor. Artif. Intell. 29(2), 433–452 (2017)
Lipton, Z.C.: The mythos of model interpretability. CoRR abs/1606.03490 (2016). http://arxiv.org/abs/1606.03490
Liu, F.T., Ting, K.M., Zhou, Z.: Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413–422, December 2008. https://doi.org/10.1109/ICDM.2008.17
Liznerski, P., Ruff, L., Vandermeulen, R.A., Franks, B.J., Kloft, M., Müller, K.R.: Explainable deep one-class classification (2021)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)
Merrick, L., Taly, A.: The explanation game: explaining machine learning models with cooperative game theory. CoRR abs/1909.08128 (2019)
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artificial Intelligence 267 (2017). https://doi.org/10.1016/j.artint.2018.07.007
Miller, T.: Contrastive explanation: a structural-model approach. Knowl. Eng. Rev. 36, e14 (2021). https://doi.org/10.1017/S0269888921000102
Montavon, G., Bach, S., Binder, A., Samek, W., Müller, K.: Explaining nonlinear classification decisions with deep Taylor decomposition. CoRR abs/1512.02479 (2015)
Navarro, D.J.: On the interaction between exemplar-based concepts and a response scaling process. Math. Psychol. 51(2), 85–98 (2007)
Nosofsky, R.M.: Attention, similarity, and the identification-categorization relationship. J. Exp. Psychol. 115(1), 39–61 (1986)
Ribeiro, M.T., Singh, S., Guestrin, C.: “why should I trust you?”: explaining the predictions of any classifier. CoRR abs/1602.04938 (2016)
Ricoeur, P.: Interpretation Theory: Discourse and the Surplus of Meaning. Texas Christian University Press, Fort Worth (1972)
Ruff, L., et al.: A unifying review of deep and shallow anomaly detection. CoRR abs/2009.11732 (2020)
Samek, W., Wiegand, T., Müller, K.: Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. CoRR abs/1708.08296 (2017)
Schölkopf, B., Platt, J.C., Shawe-Taylor, J.C., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Comput. 13(7), 1443–1471 (2001). https://doi.org/10.1162/089976601750264965
Shannon, C.E., Weaver, W.: The Mathematical Theory of Communication. University of Illinois Press, Urbana (1949)
Shepard, R.N.: Stimulus and response generalization: a stochastic model relating generalization to distance in psychological space. PsychometrikaR 22, 325–345 (1957)
Shepard, R.N.: Toward a universal law of generalization for psychological science. Science 237(4820), 1317–1323 (1987). https://doi.org/10.1126/science.3629243
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences (2017)
Sipple, J.: Interpretable, multidimensional, multimodal anomaly detection with negative sampling for detection of device failure. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 9016–9025. PMLR, 13–18 July 2020
Sipple, J., Youssef, A.: A general-purpose method for applying Explainable AI for anomaly detection (extended manuscript) (2022). https://arxiv.org/abs/2207.11564
Sundararajan, M., Najmi, A.: The many Shapley values for model explanation. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 9269–9278. PMLR, 13–18 July 2020
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. CoRR abs/1703.01365 (2017)
Tax, D.M.J., Duin, R.P.W.: Uniform object generation for optimizing one-class classifiers. J. Mach. Learn. Res. 2, 155–173 (2002)
Acknowledgements
The authors would like to thank Klaus-Robert Müller and Ankur Taly for instructive and practical advice and for their detailed technical reviews, and the anonymous reviewers for identifying gaps and suggesting improvements.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sipple, J., Youssef, A. (2022). A General-Purpose Method for Applying Explainable AI for Anomaly Detection. In: Ceci, M., Flesca, S., Masciari, E., Manco, G., Raś, Z.W. (eds) Foundations of Intelligent Systems. ISMIS 2022. Lecture Notes in Computer Science(), vol 13515. Springer, Cham. https://doi.org/10.1007/978-3-031-16564-1_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-16564-1_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16563-4
Online ISBN: 978-3-031-16564-1
eBook Packages: Computer ScienceComputer Science (R0)