Additive Explanations for Anomalies Detected from Multivariate Temporal Data
Abstract
Detecting anomalies from high-dimensional multivariate temporal data is challenging, because of the non-linear, complex relationships between signals. Recently, deep learning methods based on autoencoders have been shown to capture these relationships and accurately discern between normal and abnormal patterns of behavior, even in fully unsupervised scenarios. However, validating the anomalies detected is difficult without additional explanations. In this paper, we extend SHAP -- a unified framework for providing additive explanations, previously applied for supervised models -- with influence weighting, in order to explain anomalies detected from multivariate time series with a GRU-based autoencoder. Namely, we extract the signals that contribute most to an anomaly and those that counteract it. We evaluate our approach on two use cases and show that we can generate insightful explanations for both single and multiple anomalies.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Shapley values-based techniques such as SHAP are typically used to obtain feature contributions for explaining autoencoders.
“First of all, Shapley values-based techniques such as SHAP are typically used to obtain feature contributions for explaining AEs.”
From A Survey on Explainable Anomaly Detection (2024) · cites this paper as [72]
Nearly all deep post-model XAD techniques provide only feature-based explanations; the only exceptions are References [14,48,72], which also produce sample-based explanations.
“Second, nearly all deep post-model XAD techniques provide only feature-based explanations; the only exceptions are References [14,48,72], which also produce sample-based explanations.”
From A Survey on Explainable Anomaly Detection (2024) · cites this paper as [72]
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · see citing works
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682 · see citing works
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087 · see citing works
Andrzejak, R. G., Lehnertz, K., Mormann, F., Rieke, C., David, P., & Elger, C. E. (2001) · Physical Review E · doi:10.1103/physreve.64.061907 · Cited by 3,032 · see citing works
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761 · see citing works
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · see citing works
Zhang, C., Song, D., Chen, Y., Feng, X., Lumezanu, C., Cheng, W. D., Ni, J., Zong, B., Chen, H., & Chawla, N. V. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33011409 · Cited by 904 · see citing works
Guo, Y., Liao, W., Wang, Q., Yu, L., Ji, T., & Li, P. (2018) · Asian Conference on Machine Learning · Cited by 118 · see citing works
Zhang, C., Song, D., Chen, Y., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08055 · Cited by 98 · see citing works
Temporal Anomaly Detection: Calibrating the Surprise
Gutflaish, E., Kontorovich, A., Sivan Sabato, A., Biller, O., & Sofer, O. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013755 · Cited by 8 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Deep Learning-based Anomaly Detection in Cyber-physical Systems
Luo, Y., Xiao, Y., Cheng, L., Peng, G., & Yao, D. D. (2021) · ACM Computing Surveys · doi:10.1145/3453155 · Cited by 332 · see citing works
Review Study of Interpretation Methods for Future Interpretable Machine Learning
Mi, J., Li, A., & Zhou, L. (2020) · IEEE Access · doi:10.1109/access.2020.3032756 · Cited by 162 · see citing works
A Survey on Explainable Anomaly Detection
Li, Z., Zhu, Y., & Van Leeuwen, M. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3609333 · Cited by 139 · see citing works
“Moreover, model-specific techniques such as References [7, 31, 94] generally have consistent Explanation-Definition and Detection-Definition of anomaly as they explore the internal structure of anomaly detection model to generate explanations.”
BackgroundInfluentialSHAP Value-Based Feature Importance Analysis for Short-Term Load Forecasting
Lee, Y.-G., Oh, J.-Y., Kim, D.-S., & Kim, G. (2022) · Journal of Electrical Engineering and Technology · doi:10.1007/s42835-022-01161-9 · Cited by 115 · see citing works
Yepmo, V., Smits, G., & Pivert, O. (2022) · Data & Knowledge Engineering · doi:10.1016/j.datak.2021.101946 · Cited by 52 · see citing works
Deep Learning-Based Anomaly Detection in Cyber-Physical Systems: Progress and OpportunitiesPreprint
Luo, Y., Xiao, Y., Cheng, L., Peng, G., & Yao, D. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.13213 · Cited by 52 · see citing works
Beyond Outlier Detection: Outlier Interpretation by Attention-Guided Triplet Deviation Network
Xu, H., Wang, Y., Jian, S., Huang, Z., Wang, Y., Liu, N., & Li, F. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449868 · Cited by 40 · see citing works
Viton, F., Elbattah, M., Guérin, J.-L., & Dequen, G. (2020) · IEEE International Conference on Healthcare Informatics · doi:10.1109/ichi48887.2020.9374393 · Cited by 39 · see citing works
Contrastive Explanations for a Deep Learning Model on Time-Series Data
Labaien, J., Zugasti, E., & De Carlos, X. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-59065-9_19 · Cited by 17 · see citing works
A behavioral-based forensic investigation approach for analyzing attacks on water plants using GANs
Neshenko, N., Bou‐Harb, E., & Furht, B. (2021) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2021.301198 · Cited by 16 · see citing works
Errousso, H., Alaoui, E. A. A., Benhadou, S., & Medromi, H. (2022) · Progress in Artificial Intelligence · doi:10.1007/s13748-022-00291-5 · Cited by 14 · see citing works
DAN: Neural network based on dual attention for anomaly detection in ICS
Xu, L., Wang, B., Zhao, D., & Wu, X.-M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125766 · Cited by 14 · see citing works
Müller, R., Schreyer, M., Sattarov, T., & Borth, D. (2022) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3533271.3561667 · Cited by 13 · see citing works
Kalari, K., Christodoulis, K., Bali, N., Θεοδωροπούλου, Μ., & Tsakiroglou, C. D. (2023) · Chemical Engineering Journal · doi:10.1016/j.cej.2023.144433 · Cited by 11 · see citing works
Sengupta, A., Kundu, A., & Mukhopadhyay, A. (2024) · International Conference for Innovation in Technology (INOCON) · doi:10.1109/inocon60754.2024.10511679 · Cited by 7 · see citing works
Anomaly Attribution with Likelihood Compensation
Idé, T., Dhurandhar, A., Navrátil, J., Singh, M., & Abe, N. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i5.16535 · Cited by 6 · see citing works
On Anomaly Interpretation via Shapley ValuesPreprint
Takeishi, N., & Kawahara, Y. (2020) · arXiv (Cornell University) · Cited by 6 · see citing works
Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attribution
Idé, T., & Abe, N. (2023) · Knowledge Discovery and Data Mining · doi:10.1145/3580305.3599365 · Cited by 10 · see citing works
Explainable Unsupervised Multi-Sensor Industrial Anomaly Detection and Categorization
Ameli, M., Becker, P. A., Lankers, K., van Ackeren, M. J., Bähring, H., & Maaß, W. (2022) · International Conference on Machine Learning and Applications · doi:10.1109/icmla55696.2022.00231 · Cited by 5 · see citing works
Weighted-digraph-guided multi-kernelized learning for outlier explanation
Guan, L., Duan, L., Wang, X., Wang, H., & Lin, R. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103026 · Cited by 3 · see citing works
Enhance Reading Comprehension from EEG-Based Brain-Computer Interface
Liu, X., & Cao, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8388-9_44 · Cited by 2 · see citing works
Automatic detection of rare observations during production tests using statistical models
Mourer, A., Lacaille, J., Olteanu, M., & Marie Chavent, A. (2020) · Annual Conference of the PHM Society · doi:10.36001/phmconf.2020.v12i1.1136 · Cited by 1 · see citing works
Evaluating Anomaly Explanations Using Ground Truth
Antwarg, L., Galed, C., Rokach, L., & Shapira, B. (2024) · AI · doi:10.3390/ai5040117 · Cited by 1 · see citing works
Anomaly Detection and Interpretation from Tabular Data Using Transformer Architecture
Homayouni, H., Aghayarzadeh, H., Ray, I., & Shirazi, H. M. (2024) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw65004.2024.00091 · Cited by 1 · see citing works
On Predictive Explanation of Data AnomaliesPreprint
Myrtakis, N., Tsamardinos, I., & Christophides, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.09467
Cyber Situational Awareness for Industrial Control Systems (ICSs) Deployed in Smart City
Neshenko, N., Bou‐Harb, E., & Furht, B. (2022) · Springer eBooks · doi:10.1007/978-3-031-18464-2_4
Deviation-Sensitive Black-Box Anomaly Attribution
Idé, T. (2025) · Springer eBooks · doi:10.1007/978-981-96-9108-1_6
- Authors
- Giurgiu, I., & Schumann, A.
- Affiliations
- IBM Research - Zurich (CH)
- ORCID
- Giurgiu, Ioana
- Venue
- Proceedings of the 28th ACM International Conference on Information and Knowledge Management
- Publisher
- ACM
- Published
- 2019-11-03
- Pages
- 2245-2248
- ISSN
- 2155-0751 (ISSN-L)
- OpenAlex
- W2985323229
- Cited by
- 27
- References
- 9
- Citations by year
- 2025: 2 · 2024: 4 · 2023: 4 · 2022: 5 · 2021: 6 · 2020: 6
- FWCI
- 1.63
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Information and Knowledge Management (CIKM) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Keywords
- anomaly detection, multivariate time series, SHAP, unsupervised anomaly detection, explainable deep learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
