“…In Table 4 we refer to this type of explanation as author-selected examples. Such first demonstrations give insights into the model as well as into the data used [61], [83], [101], [162]. However, these visual approaches are highly qualitative evaluations given that in most cases, only small-scale studies with a limited amount of users are undertaken.…”
Section: B Evaluationmentioning
confidence: 99%
“…Quality metrics that are applied in such cases often use the underlying training metrics such as accuracy (ACC) or area under the receiver operating characteristic curve (AUROC). Examples for such evaluations using accuracy are [7], [62], [83], [111], [162], AUROC [67], [68], AUPRC (area under the precision-recall curve) [67], [164].…”
Section: B Evaluationmentioning
confidence: 99%
“…Besides the focus on individual time points, they also propose perturbation strategies to evaluate the time constraints. Both, [162] and [7], suggest that there is not one best explanation method to use for all models, but rather a heavy dependence on the applied model's approach.…”
Time series data is increasingly used in a wide range of fields, and it is often relied on in crucial applications and high-stakes decision-making. For instance, sensors generate time series data to recognize different types of anomalies through automatic decision-making systems. Typically, these systems are realized with machine learning models that achieve top-tier performance on time series classification tasks. Unfortunately, the logic behind their prediction is opaque and hard to understand from a human standpoint. Recently, we observed a consistent increase in the development of explanation methods for time series classification justifying the need to structure and review the field. In this work, we (a) present the first extensive literature review on Explainable AI (XAI) for time series classification, (b) categorize the research field through a taxonomy subdividing the methods into time points-based, subsequences-based and instance-based, and (c) identify open research directions research directions regarding the type of explanations and the evaluation of explanations and interpretability.
“…In Table 4 we refer to this type of explanation as author-selected examples. Such first demonstrations give insights into the model as well as into the data used [61], [83], [101], [162]. However, these visual approaches are highly qualitative evaluations given that in most cases, only small-scale studies with a limited amount of users are undertaken.…”
Section: B Evaluationmentioning
confidence: 99%
“…Quality metrics that are applied in such cases often use the underlying training metrics such as accuracy (ACC) or area under the receiver operating characteristic curve (AUROC). Examples for such evaluations using accuracy are [7], [62], [83], [111], [162], AUROC [67], [68], AUPRC (area under the precision-recall curve) [67], [164].…”
Section: B Evaluationmentioning
confidence: 99%
“…Besides the focus on individual time points, they also propose perturbation strategies to evaluate the time constraints. Both, [162] and [7], suggest that there is not one best explanation method to use for all models, but rather a heavy dependence on the applied model's approach.…”
Time series data is increasingly used in a wide range of fields, and it is often relied on in crucial applications and high-stakes decision-making. For instance, sensors generate time series data to recognize different types of anomalies through automatic decision-making systems. Typically, these systems are realized with machine learning models that achieve top-tier performance on time series classification tasks. Unfortunately, the logic behind their prediction is opaque and hard to understand from a human standpoint. Recently, we observed a consistent increase in the development of explanation methods for time series classification justifying the need to structure and review the field. In this work, we (a) present the first extensive literature review on Explainable AI (XAI) for time series classification, (b) categorize the research field through a taxonomy subdividing the methods into time points-based, subsequences-based and instance-based, and (c) identify open research directions research directions regarding the type of explanations and the evaluation of explanations and interpretability.
“…This paper proposes TimeREISE, an instance-based attribution method applicable to every classifier. It addresses common bottlenecks such as runtime, smoothness, and robustness against input perturbations as mentioned in [10]. The rest of the paper shows that the explanations provided by TimeREISE are continuous, precise and robust.…”
Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safety critical context. The research field of explainable artificial intelligence addresses this problem. However, most of the interpretability methods are aligned to the image modality by design. The paper introduces TimeREISE a model agnostic attribution method specifically aligned to success in the context of time series classification. The method shows superior performance compared to existing approaches concerning different well-established measurements. TimeREISE is applicable to any time series classification network, its runtime does not scale in a linear manner concerning the input shape and it does not rely on prior data knowledge.
“…This paper proposes TimeREISE, an instance-based attribution method applicable to every classifier. It addresses common bottlenecks such as runtime, smoothness, and robustness against input perturbations as mentioned in [11]. Many methods suffer from large computation times making them unfeasible for real-time applications.…”
Deep neural networks are one of the most successful classifiers across different domains. However, their use is limited in safety-critical areas due to their limitations concerning interpretability. The research field of explainable artificial intelligence addresses this problem. However, most interpretability methods align to the imaging modality by design. The paper introduces TimeREISE, a model agnostic attribution method that shows success in the context of time series classification. The method applies perturbations to the input and considers different attribution map characteristics such as the granularity and density of an attribution map. The approach demonstrates superior performance compared to existing methods concerning different well-established measurements. TimeREISE shows impressive results in the deletion and insertion test, Infidelity, and Sensitivity. Concerning the continuity of an explanation, it showed superior performance while preserving the correctness of the attribution map. Additional sanity checks prove the correctness of the approach and its dependency on the model parameters. TimeREISE scales well with an increasing number of channels and timesteps. TimeREISE applies to any time series classification network and does not rely on prior data knowledge. TimeREISE is suited for any usecase independent of dataset characteristics such as sequence length, channel number, and number of classes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.