research-article

Reliable Counterfactual Explanations for Autoencoder based Anomalies

Authors:

Swastik Haldar,

Philips George John,

Diptikalyan SahaAuthors Info & Claims

CODS-COMAD '21: Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)

Pages 83 - 91

https://doi.org/10.1145/3430984.3431015

Published: 02 January 2021 Publication History

Abstract

Autoencoders have been used successfully for tackling the problem of anomaly detection in an unsupervised setting, and are often known to give better results than traditional approaches such as clustering and subspace-based (linear) methods. A data point is flagged as anomalous by an autoencoder if its reconstruction loss is higher than an appropriate threshold. However, as with other deep learning models, the increased accuracy offered by autoencoders comes at the cost of interpretability. Explaining an autoencoder’s decision to flag a particular data point as an anomaly is greatly important, since a human-friendly explanation would be necessary for a domain expert tasked with evaluating the model’s decisions. We consider the problem of finding counterfactual explanations for autoencoder anomalies, which address the question of what needs to be minimally changed in a given anomalous data point to make it non-anomalous. We present an algorithm that generates a diverse set of proximate counterfactual explanations for a given autoencoder anomaly. We also introduce the notion of reliability of a counterfactual, and present techniques to find reliable counterfactual explanations.

References

[1]

Liat Antwarg, Bracha Shapira, and Lior Rokach. 2019. Explaining Anomalies Detected by Autoencoders Using SHAP. CoRR abs/1903.02407(2019), 5. arxiv:1903.02407http://arxiv.org/abs/1903.02407

[2]

Anirban Chakraborty, Manaar Alam, Vishal Dey, Anupam Chattopadhyay, and Debdeep Mukhopadhyay. 2018. Adversarial Attacks and Defences: A Survey. CoRR abs/1810.00069(2018), 31. arxiv:1810.00069http://arxiv.org/abs/1810.00069

[3]

Alberto Costa and Giacomo Nannicini. 2018. RBFOpt: an open-source library for black-box optimization with costly function evaluations. Mathematical Programming Computation 10 (08 2018), 33. https://doi.org/10.1007/s12532-018-0144-7

[4]

Ian Davidson. 2007. Anomaly Detection, Explanation and Visualization. https://web.cs.ucdavis.edu/~davidson/Publications/anomalyDetectionExternal.pdf. SGI. Tech. Rep.

[5]

Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. http://archive.ics.uci.edu/ml. University of California, Irvine, School of Information and Computer Sciences.

[6]

Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press, USA. http://www.deeplearningbook.org.

Digital Library

[7]

Amir-Hossein Karimi, Gilles Barthe, Borja Balle, and Isabel Valera. 2019. Model-Agnostic Counterfactual Explanations for Consequential Decisions. CoRR abs/1905.11190(2019), 14. arxiv:1905.11190http://arxiv.org/abs/1905.11190

[8]

Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems 30, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett(Eds.). Curran Associates, Inc., USA, 4765–4774. http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf

[9]

S. Moro, P. Cortez, and P. Rita. 2014. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems 62 (Jun 2014), 22–31.

[10]

Ramaravind Kommiya Mothilal, Amit Sharma, and Chenhao Tan. 2020. Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations. In Proceedings of the ACM Conference on Fairness, Accountability, and Transparency.ACM, New York, USA, 607–617.

Digital Library

[11]

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32. Curran Associates, Inc., USA, 8024–8035.

Digital Library

[12]

Shebuti Rayana. 2016. Outlier Detection Datasets (ODDS) Library. http://odds.cs.stonybrook.edu/. Stony Brook University, Department of Computer Science.

[13]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. ”Why Should I Trust You?”: Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, USA, 1135–1144.

Digital Library

[14]

D. E. Rumelhart, G. E. Hinton, and R. J. Williams. 1986. Learning Internal Representations by Error Propagation. MIT Press, Cambridge, MA, USA, 318–362.

[15]

Chris Russell. 2019. Efficient Search for Diverse Coherent Explanations. In Proceedings of the Conference on Fairness, Accountability, and Transparency (Atlanta, GA, USA) (FAT* ’19). Association for Computing Machinery, New York, NY, USA, 20–28. https://doi.org/10.1145/3287560.3287569

Digital Library

[16]

Mayu Sakurada and Takehisa Yairi. 2014. Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction. In Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis (Gold Coast, Australia QLD, Australia) (MLSDA’14). Association for Computing Machinery, New York, NY, USA, 4–11. https://doi.org/10.1145/2689746.2689747

Digital Library

[17]

Md Amran Siddiqui, Alan Fern, Thomas G. Dietterich, and Weng-Keen Wong. 2019. Sequential Feature Explanations for Anomaly Detection. ACM Trans. Knowl. Discov. Data 13, 1, Article 1 (Jan. 2019), 22 pages. https://doi.org/10.1145/3230666

Digital Library

[18]

N. Takeishi. 2019. Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detection. In 2019 International Conference on Data Mining Workshops (ICDMW). IEEE, USA, 793–798.

[19]

Berk Ustun, Alexander Spangher, and Yang Liu. 2019. Actionable Recourse in Linear Classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency (Atlanta, GA, USA) (FAT* ’19). Association for Computing Machinery, New York, NY, USA, 10–19. https://doi.org/10.1145/3287560.3287566

Digital Library

[20]

Sandra Wachter, Brent D. Mittelstadt, and Chris Russell. 2017. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. CoRR abs/1711.00399(2017), 52. arxiv:1711.00399http://arxiv.org/abs/1711.00399

[21]

Chong Zhou and Randy C. Paffenroth. 2017. Anomaly Detection with Robust Deep Autoencoders. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Halifax, NS, Canada) (KDD ’17). Association for Computing Machinery, New York, NY, USA, 665–674. https://doi.org/10.1145/3097983.3098052

Digital Library

Cited By

Antwarg Friedman LGaled CRokach LShapira B(2024)Evaluating Anomaly Explanations Using Ground TruthAI10.3390/ai50401175:4(2375-2392)Online publication date: 15-Nov-2024
https://doi.org/10.3390/ai5040117
Verma SBoonsanong VHoang MHines KDickerson JShah C(2024)Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A ReviewACM Computing Surveys10.1145/367711956:12(1-42)Online publication date: 9-Jul-2024
https://dl.acm.org/doi/10.1145/3677119
Jakubik JKwaśnicka HLi XHandl J(2024)Drawing Attributions From Evolved CounterfactualsProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3638530.3664122(1582-1589)Online publication date: 14-Jul-2024
https://dl.acm.org/doi/10.1145/3638530.3664122
Show More Cited By

Recommendations

Achieving Counterfactual Explanation for Sequence Anomaly Detection
Machine Learning and Knowledge Discovery in Databases. Research Track and Demo Track
Abstract
Anomaly detection on discrete sequential data has been investigated for a long time because of its potential in various applications, such as detecting novel attacks or abnormal system behaviors from log messages. Although many approaches can ...
On generating trustworthy counterfactual explanations
Abstract
Deep learning models like chatGPT exemplify AI success but necessitate a deeper understanding of trust in critical sectors. Trust can be achieved using counterfactual explanations, which is how humans become familiar with unknown processes; by ...
Highlights
- Trustworthy counterfactuals: plausibility, change intensity, adversarial power.
- Reliability: detecting bias and data misrepresentation in deep learning models.
- Generating realistic counterfactual examples for improved trust in deep ...
Detecting Anomalies with Autoencoders on Data Streams
Machine Learning and Knowledge Discovery in Databases
Abstract
Autoencoders have achieved impressive results in anomaly detection tasks by identifying anomalous data as instances that do not match their learned representation of normality. To this end, autoencoders are typically trained on large amounts of ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

CODS-COMAD '21: Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)

January 2021

453 pages

ISBN:9781450388177

DOI:10.1145/3430984

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 02 January 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

CODS COMAD 2021

CODS COMAD 2021: 8th ACM IKDD CODS and 26th COMAD

January 2 - 4, 2021

Bangalore, India

Acceptance Rates

Overall Acceptance Rate 197 of 680 submissions, 29%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

8
Total Citations
View Citations
412
Total Downloads

Downloads (Last 12 months)94
Downloads (Last 6 weeks)10

Reflects downloads up to 12 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Antwarg Friedman LGaled CRokach LShapira B(2024)Evaluating Anomaly Explanations Using Ground TruthAI10.3390/ai50401175:4(2375-2392)Online publication date: 15-Nov-2024
https://doi.org/10.3390/ai5040117
Verma SBoonsanong VHoang MHines KDickerson JShah C(2024)Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A ReviewACM Computing Surveys10.1145/367711956:12(1-42)Online publication date: 9-Jul-2024
https://dl.acm.org/doi/10.1145/3677119
Jakubik JKwaśnicka HLi XHandl J(2024)Drawing Attributions From Evolved CounterfactualsProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3638530.3664122(1582-1589)Online publication date: 14-Jul-2024
https://dl.acm.org/doi/10.1145/3638530.3664122
Lanvin MGimenez PHan YMajorczyk FMé LTotel E(2023)Towards Understanding Alerts raised by Unsupervised Network Intrusion Detection SystemsProceedings of the 26th International Symposium on Research in Attacks, Intrusions and Defenses10.1145/3607199.3607247(135-150)Online publication date: 16-Oct-2023
https://dl.acm.org/doi/10.1145/3607199.3607247
Chinu Bansal U(2023)Explainable AI: To Reveal the Logic of Black-Box ModelsNew Generation Computing10.1007/s00354-022-00201-242:1(53-87)Online publication date: 1-Feb-2023
https://doi.org/10.1007/s00354-022-00201-2
Datta DChen FRamakrishnan NZhang ARangwala H(2022)Framing Algorithmic Recourse for Anomaly DetectionProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3534678.3539344(283-293)Online publication date: 14-Aug-2022
https://doi.org/10.1145/3534678.3539344
Smits GLesot MYepmo Tchaghe VPivert O(2022)PANDA: Human-in-the-Loop Anomaly Detection and ExplanationInformation Processing and Management of Uncertainty in Knowledge-Based Systems10.1007/978-3-031-08974-9_57(720-732)Online publication date: 4-Jul-2022
https://doi.org/10.1007/978-3-031-08974-9_57
Tchaghe VSmits GPivert O(2022)A Classification of Anomaly Explanation MethodsMachine Learning and Principles and Practice of Knowledge Discovery in Databases10.1007/978-3-030-93736-2_3(26-33)Online publication date: 17-Feb-2022
https://doi.org/10.1007/978-3-030-93736-2_3
Tchaghe VSmits GPivert O(2021)Anomaly explanation: A reviewData & Knowledge Engineering10.1016/j.datak.2021.101946(101946)Online publication date: Nov-2021
https://doi.org/10.1016/j.datak.2021.101946

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents