# Explaining Time Series Classification Predictions via Causal Attributions

arXiv: https://arxiv.org/abs/2405.15871 · HTML: https://mlsanity.com/paper/2405.15871/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 76 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 30 of 32)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models](https://mlsanity.com/paper/2208.09399/) (2022)
- [Deep learning-based electroencephalography analysis: a systematic review](https://mlsanity.com/paper/1901.05498/) (2019)
- [LSTM Fully Convolutional Networks for Time Series Classification](https://mlsanity.com/paper/1709.05206/) (2017)
- [Explaining Classifiers with Causal Concept Effect (CaCE)](https://mlsanity.com/paper/1907.07165/) (2019)
- [Deep Learning for Sensor-based Activity Recognition: A Survey](https://mlsanity.com/paper/1707.03502/) (2017)
- [Benchmarking Deep Learning Interpretability in Time Series Predictions](https://mlsanity.com/paper/2010.13924/) (2020)
- [Self-attention for raw optical Satellite Time Series Classification](https://mlsanity.com/paper/1910.10536/) (2019)
- [Explaining Time Series Predictions with Dynamic Masks](https://mlsanity.com/paper/2106.05303/) (2021)
- [Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey](https://mlsanity.com/paper/2104.00950/) (2021)
- [A Time Series Forest for Classification and Feature Extraction](https://mlsanity.com/paper/1302.2277/) (2013)
- [Instance-based Counterfactual Explanations for Time Series Classification](https://mlsanity.com/paper/2009.13211/) (2020)
- [A Closer Look at AUROC and AUPRC under Class Imbalance](https://mlsanity.com/paper/2401.06091/) (2024)
- [Counterfactual Explanations for Machine Learning on Multivariate Time Series Data](https://mlsanity.com/paper/2008.10781/) (2020)
- [Diffusion-based Conditional ECG Generation with Structured State Space Models](https://mlsanity.com/paper/2301.08227/) (2023)
- [TAnoGAN: Time Series Anomaly Detection with Generative Adversarial Networks](https://mlsanity.com/paper/2008.09567/) (2020)
- [Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks](https://mlsanity.com/paper/2401.06654/) (2024)
- [PredDiff: Explanations and Interactions from Conditional Expectations](https://mlsanity.com/paper/2102.13519/) (2021)
- [Interpretation of Time-Series Deep Models: A Survey](https://mlsanity.com/paper/2305.14582/) (2023)
- [Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery](https://mlsanity.com/paper/2305.17043/) (2023)
- [Motif-guided Time Series Counterfactual Explanations](https://mlsanity.com/paper/2211.04411/) (2022)

## Built on by (most cited first, 4 of 4)

- [Enhancing clinical decision support with physiological waveforms -- a multimodal benchmark in emergency care](https://mlsanity.com/paper/2407.17856/) (2024)
- [Explainable machine learning for neoplasms diagnosis via electrocardiograms: an externally validated study](https://mlsanity.com/paper/2412.07737/) (2024)
- [Electrocardiogram-based diagnosis of liver diseases: an externally validated and explainable machine learning approach](https://mlsanity.com/paper/2412.03717/) (2024)
- [A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking](https://mlsanity.com/paper/2601.06645/) (2026)

## Abstract (arXiv)

Despite the excelling performance of machine learning models, understanding their decisions remains a long-standing goal. Although commonly used attribution methods from explainable AI attempt to address this issue, they typically rely on associational rather than causal relationships. In this study, within the context of time series classification, we introduce a novel model-agnostic attribution method to assess the causal effect of concepts i.e., predefined segments within a time series, on classification outcomes. Our approach compares these causal attributions with closely related associational attributions, both theoretically and empirically. To estimate counterfactual outcomes, we use state-of-the-art diffusion models backed by state space models. We demonstrate the insights gained by our approach for a diverse set of qualitatively different time series classification tasks. Although causal and associational attributions might often share some similarities, in all cases they differ in important details, underscoring the risks associated with drawing causal conclusions from associational data alone. We believe that the proposed approach is also widely applicable in other domains to shed some light on the limits of associational attributions.