Time series saliency maps: explaining models across multiple domains
Traditional saliency map methods, popularized in computer vision, highlight individual points (pixels) of the input that contribute the most to the model's output. However, in time-series they offer limited insights as semantically meaningful features are often found in other domains. We introduce Cross-domain Integrated Gradients, a generalization of Integrated Gradients. Our method enables feature attributions on any domain that can be formulated as an invertible, differentiable transformation of the time domain. Crucially, our derivation extends the original Integrated Gradients into the complex domain, enabling frequency-based attributions. We provide the necessary theoretical guarantees, namely, path independence and completeness. Our approach reveals interpretable, problem-specific attributions that time-domain methods cannot capture, on three real-world tasks: wearable sensor heart rate extraction, electroencephalography-based seizure detection, and zero-shot time-series forecasting. We release an open-source Tensorflow/PyTorch library to enable plug-and-play cross-domain explainability for time-series models. These results demonstrate the ability of cross-domain integrated gradients to provide semantically meaningful insights in time-series models that are impossible with traditional time-domain saliency.
Code (2)
Tasks
Explainable Artificial Intelligence (XAI)Interpretability Techniques for Deep LearningPhotoplethysmography (PPG) heart rate estimationSeizure DetectionTime SeriesTime Series ForecastingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FreqRISE: Explaining time series using frequency masking
Time-series data are fundamentally important for many critical domains such as healthcare, finance, and climate, where explainable models are necessary for safe automated decision making. To develop explainable artificia…
Decision MakingExplainable artificial intelligenceExplainable ModelsTime SeriesFLEXtime: Filterbank learning to explain time series
State-of-the-art methods for explaining predictions from time series involve learning an instance-wise saliency mask for each time step; however, many types of time series are difficult to interpret in the time domain, d…
EEGTime SeriesSaliency Maps Give a False Sense of Explanability to Image Classifiers: An Empirical Evaluation across Methods and Metrics
The interpretability of deep neural networks (DNNs) has emerged as a crucial area of research, particularly in image classification tasks where decisions often lack transparency. Saliency maps have been widely used as …
image-classificationImage ClassificationClass-Specific Explainability for Deep Time Series Classifiers
Explainability helps users trust deep learning solutions for time series classification. However, existing explainability methods for multi-class time series classifiers focus on one class at a time, ignoring relationshi…
Time SeriesTime Series AnalysisTime Series ClassificationTemporal Saliency Detection Towards Explainable Transformer-based Timeseries Forecasting
Despite the notable advancements in numerous Transformer-based models, the task of long multi-horizon time series forecasting remains a persistent challenge, especially towards explainability. Focusing on commonly used s…
DecoderSaliency DetectionTime SeriesTime Series Analysis+3