# Evaluating Explanation Methods for Multivariate Time Series Classification

arXiv: https://arxiv.org/abs/2308.15223 · HTML: https://mlsanity.com/paper/2308.15223/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 29 Aug 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification](https://mlsanity.com/paper/2012.08791/) (2020)
- [Benchmarking Deep Learning Interpretability in Time Series Predictions](https://mlsanity.com/paper/2010.13924/) (2020)
- [MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification](https://mlsanity.com/paper/2102.00457/) (2021)
- [Explaining Time Series Predictions with Dynamic Masks](https://mlsanity.com/paper/2106.05303/) (2021)
- [Evaluation of post-hoc interpretability methods in time-series classification](https://mlsanity.com/paper/2202.05656/) (2022)
- [Interpretable Time Series Classification using Linear Models and Multi-resolution Multi-domain Symbolic Representations](https://mlsanity.com/paper/2006.01667/) (2020)
- [WEASEL 2.0 -- A Random Dilated Dictionary Transform for Fast, Accurate and Memory Constrained Time Series Classification](https://mlsanity.com/paper/2301.10194/) (2023)
- [dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification](https://mlsanity.com/paper/2207.12165/) (2022)
- [timeXplain -- A Framework for Explaining the Predictions of Time Series Classifiers](https://mlsanity.com/paper/2007.07606/) (2020)
- [Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifiers](https://mlsanity.com/paper/2210.00507/) (2022)
- [Robust Explainer Recommendation for Time Series Classification](https://mlsanity.com/paper/2306.05501/) (2023)

## Built on by (most cited first, 2 of 2)

- [Improving the Evaluation and Actionability of Explanation Methods for Multivariate Time Series Classification](https://mlsanity.com/paper/2406.12507/) (2024)
- [Scaling Time Series Classification via XAI-Driven Data Reduction](https://mlsanity.com/paper/2607.15774/) (2026)

## Abstract (arXiv)

Multivariate time series classification is an important computational task arising in applications where data is recorded over time and over multiple channels. For example, a smartwatch can record the acceleration and orientation of a person's motion, and these signals are recorded as multivariate time series. We can classify this data to understand and predict human movement and various properties such as fitness levels. In many applications classification alone is not enough, we often need to classify but also understand what the model learns (e.g., why was a prediction given, based on what information in the data). The main focus of this paper is on analysing and evaluating explanation methods tailored to Multivariate Time Series Classification (MTSC). We focus on saliency-based explanation methods that can point out the most relevant channels and time series points for the classification decision. We analyse two popular and accurate multivariate time series classifiers, ROCKET and dResNet, as well as two popular explanation methods, SHAP and dCAM. We study these methods on 3 synthetic datasets and 2 real-world datasets and provide a quantitative and qualitative analysis of the explanations provided. We find that flattening the multivariate datasets by concatenating the channels works as well as using multivariate classifiers directly and adaptations of SHAP for MTSC work quite well. Additionally, we also find that the popular synthetic datasets we used are not suitable for time series analysis.