Explainable Time Series Tweaking via Irreversible and Reversible Temporal Transformations
Open accessAbstract
Time series classification has received great attention over the past decade with a wide range of methods focusing on predictive performance by exploiting various types of temporal features. Nonetheless, little emphasis has been placed on interpretability and explainability. In this paper, we formulate the novel problem of explainable time series tweaking, where, given a time series and an opaque classifier that provides a particular classification decision for the time series, we want to find the minimum number of changes to be performed to the given time series so that the classifier changes its decision to another class. We show that the problem is NP-hard, and focus on two instantiations of the problem, which we refer to as reversible and irreversible time series tweaking. The classifier under investigation is the random shapelet forest classifier. Moreover, we propose two algorithmic solutions for the two problems along with simple optimizations, as well as a baseline solution using the nearest neighbor classifier. An extensive experimental evaluation on a variety of real datasets demonstrates the usefulness and effectiveness of our problem formulation and solutions.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Besides using Incremental Deletion/Addition to evaluate correctness and output-completeness, compactness can be evaluated by counting how many features of the explanation need to be removed, perturbed or added to change the decision of the predictive model.
“Besides using Incremental Deletion/Addition to evaluate correctness and output-completeness, compactness can be evaluated by counting how many features of the explanation need to be removed, perturbed or added to change the decision of the predictive model [7,34,70,123,165,221].”
From From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2023) · cites this paper as [123]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486 · see citing works
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555 · see citing works
Dynamic Programming Algorithm Optimization for Spoken Word Recognition
Sakoe, H., & Chiba, S. (1978) · IEEE Transactions on Acoustics Speech and Signal Processing · doi:10.1109/tassp.1978.1163055 · Cited by 6,727 · see citing works
The mythos of model interpretability
Lipton, Z. C. (2018) · Communications of the ACM · doi:10.1145/3233231 · Cited by 5,427 · 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
Querying and mining of time series data
Ding, H., Trajcevski, G., Scheuermann, P., Wang, X., & Keogh, E. (2008) · Proceedings of the VLDB Endowment · doi:10.14778/1454159.1454226 · Cited by 1,353 · see citing works
Robust and fast similarity search for moving object trajectories
Chen, L., ÖZSU, M. T., & Oria, V. (2005) · Proceedings - ACM-SIGMOD International Conference on Management of Data · doi:10.1145/1066157.1066213 · Cited by 1,349 · see citing works
On The Marriage of Lp-norms and Edit Distance
Chen, L., & Ng, R. T. (2004) · Elsevier eBooks · doi:10.1016/b978-012088469-8.50070-x · Cited by 715 · see citing works
A time series forest for classification and feature extraction
Deng, H., Runger, G. C., Tuv, E., & Vladimir, M. (2013) · Information Sciences · doi:10.1016/j.ins.2013.02.030 · Cited by 632 · see citing works
The Complexity of Some Problems on Subsequences and Supersequences
Maier, D. (1978) · Journal of the ACM · doi:10.1145/322063.322075 · Cited by 617 · see citing works
"Why Should I Trust You?": Explaining the Predictions of Any ClassifierPreprint
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.04938 · Cited by 587 · see citing works
Turney, P. D. (1995) · Journal of Artificial Intelligence Research · doi:10.1613/jair.120 · Cited by 570 · see citing works
Classification of time series by shapelet transformation
Hills, J., Lines, J., Baranauskas, E., Mapp, J., & Bagnall, A. (2014) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-013-0322-1 · Cited by 538 · see citing works
Learning time-series shapelets
Grabocka, J., Schilling, N., Wistuba, M., & Schmidt-Thieme, L. (2014) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2623330.2623613 · Cited by 489 · see citing works
Time series shapelets: a novel technique that allows accurate, interpretable and fast classification
Ye, L., & Keogh, E. (2011) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-010-0179-5 · Cited by 406 · see citing works
A shapelet transform for time series classification
Lines, J., Davis, L. M., Hills, J., & Bagnall, A. J. (2012) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2339530.2339579 · Cited by 380 · see citing works
A Bag-of-Features Framework to Classify Time Series
Baydogan, M. G., Runger, G., & Tuv, E. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.72 · Cited by 361 · see citing works
Highly Comparative Feature-Based Time-Series Classification
Fulcher, B., & Jones, N. S. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2014.2316504 · Cited by 346 · see citing works
Everything you know about Dynamic Time Warping is Wrong
Ratanamahatana, C. A., & Keogh, E. (2004) · Cited by 300 · see citing works
SAX-VSM: Interpretable Time Series Classification Using SAX and Vector Space Model
Senin, P., & Malinchik, S. (2013) · Proceedings · doi:10.1109/icdm.2013.52 · Cited by 254 · see citing works
(2012) · Cited by 253 · see citing works
Heartbeat Time Series Classification With Support Vector Machines
Kampouraki, A., Manis, G., & Nikou, C. (2009) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2008.2003323 · Cited by 252 · see citing works
Feature-based classification of time-series data
Νανόπουλος, Α., Alcock, R. J., & Manolopoulos, Y. (2001) · Cited by 251 · see citing works
Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking
Tolomei, G., Silvestri, F., Haines, A., & Lalmas, M. (2017) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3097983.3098039 · Cited by 192 · see citing works
Extracting Interpretable Features for Early Classification on Time Series
Xing, Z., Pei, J., Yu, P. S., et al. (2011) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972818.22 · Cited by 178 · see citing works
Generalized random shapelet forests
Karlsson, I., Papapetrou, P., & Boström, H. (2016) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-016-0473-y · Cited by 170 · see citing works
Self-citationOn The Marriage of Lp-norms and Edit Distance
CHEN, L., & NG, R. (2004) · Elsevier eBooks · doi:10.1016/b978-012088469-8/50070-x · Cited by 161 · see citing works
Finding anomalous periodic time series
Rebbapragada, U. D., Protopapas, P., Brodley, C. E., & Alcock, C. R. (2008) · Machine Learning · doi:10.1007/s10994-008-5093-3 · Cited by 156 · see citing works
Optimal Action Extraction for Random Forests and Boosted Trees
Cui, Z., Chen, W., He, Y., et al. (2015) · ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2783258.2783281 · Cited by 109 · see citing works
Karim, M., & Rahman, R. M. (2013) · Journal of Software Engineering and Applications · doi:10.4236/jsea.2013.64025 · Cited by 103 · see citing works
Support vector machines of interval-based features for time series classification
Rodríguez, J. J., Alonso, C. J., & Maestro, J. A. (2005) · Knowledge-Based Systems · doi:10.1016/j.knosys.2004.10.007 · Cited by 91 · see citing works
Extracting Actionable Knowledge from Decision Trees
Yang, Q., Yin, J., Ling, C. X., & Pan, R. (2006) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2007.250584 · Cited by 86 · see citing works
Extracting Actionable Knowledge from Decision Trees
Yang, Q., Member, S., Yin, J., Ling, C., & Pan, R. (2007) · doi:10.1109/tkde.2007.10 · Cited by 75 · see citing works
Time-series classification with COTE: The collective of transformation-based ensembles
Bagnall, A. J., Lines, J., Hills, J., & Bostrom, A. G. (2016) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2016.7498418 · Cited by 63 · see citing works
Ultra-Fast Shapelets for Time Series ClassificationPreprint
Wistuba, M., Grabocka, J., & Schmidt-Thieme, L. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.05018 · Cited by 60 · see citing works
Bejar, D., COLOMBO, P. C., Latif, F., & yuzefpolskaya, M. (2015) · Clinical Medicine Insights Cardiology · doi:10.4137/cmc.s19706 · Cited by 55 · see citing works
Shapelet Ensemble for Multi-dimensional Time Series
Cetin, M. S., Mueen, A., & Calhoun, V. D. (2015) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611974010.35 · Cited by 40 · see citing works
Extracting discriminative shapelets from heterogeneous sensor data
Patri, O. P., Sharma, A. B., Chen, H., Jiang, G., Panangadan, A. V., & Prasanna, V. K. (2014) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2014.7004344 · Cited by 24 · see citing works
Efficient Action Extraction with Many-to-Many Relationship between Actions and Features
Du, J., Hu, Y. Q., Ling, C. X., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24130-7_29 · Cited by 9 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- J. Grabocka, N. Schilling, M. Wistuba, and L. Schmidt-Thieme, "Learn- ing time-series shapelets." in Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2014, pp. 392-401.
- I. Karlsson, P. Papapetrou, and H. Boström, "Generalized forests," Data Min. Knowl. Discov., vol. 30, no. 5, pp. 1053-1085, 2016.
Cited by
Sorted by citations
Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590 · see citing works
Counterfactual Explanations for Multivariate Time Series
Ates, E., Aksar, B., Leung, V. J., & Coskun, A. K. (2021) · 2021 International Conference on Applied Artificial Intelligence (ICAPAI) · doi:10.1109/icapai49758.2021.9462056 · Cited by 88 · see citing works
- Authors
- Karlsson, I., Rebane, J., Papapetrou, P., & Gionis, A.
- Affiliations
- Stockholm University (SE)
- Aalto University (FI)
- Venue
- 2018 IEEE International Conference on Data Mining (ICDM)
- Publisher
- IEEE
- Published
- 2018-11
- Pages
- 207-216
- ISSN
- 1550-4786 (ISSN-L)
- OpenAlex
- W2892285692
- Cited by
- 31
- References
- 39
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 5 · 2023: 6 · 2022: 5 · 2021: 9 · 2020: 1 · 2019: 3
- FWCI
- 2.48
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- other-oa
- Locations
- Proceedings (publishedVersion)
- Aaltodoc (Aalto University) (submittedVersion, other-oa)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Academy of Finland
- Stockholms Läns Landsting
- Horizon 2020 Framework Programme (EC H2020, 654024)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications
- Keywords
- time series classification, interpretability, NP-hardness, nearest neighbor classification, temporal feature engineering
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
