# Time to Focus: A Comprehensive Benchmark Using Time Series Attribution Methods

arXiv: https://arxiv.org/abs/2202.03759 · HTML: https://mlsanity.com/paper/2202.03759/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 8 Feb 2022.

## Builds on (most cited first, 18 of 18)

- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020)
- [Visual Interpretability for Deep Learning: a Survey](https://mlsanity.com/paper/1802.00614/) (2018)
- [Sampling Permutations for Shapley Value Estimation](https://mlsanity.com/paper/2104.12199/) (2021)
- [Explaining Time Series Predictions with Dynamic Masks](https://mlsanity.com/paper/2106.05303/) (2021)
- [Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks](https://mlsanity.com/paper/2107.11400/) (2021)
- [TSViz: Demystification of Deep Learning Models for Time-Series Analysis](https://mlsanity.com/paper/1802.02952/) (2018)
- [How to choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice](https://mlsanity.com/paper/2107.04427/) (2021)
- [Impact of Legal Requirements on Explainability in Machine Learning](https://mlsanity.com/paper/2007.05479/) (2020)

## Built on by (most cited first, 8 of 8)

- [A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI](https://mlsanity.com/paper/2307.05104/) (2023)
- [Right on Time: Revising Time Series Models by Constraining their Explanations](https://mlsanity.com/paper/2402.12921/) (2024)
- [TimeREISE: Time-series Randomized Evolving Input Sample Explanation](https://mlsanity.com/paper/2202.07952/) (2022)
- [Class-Dependent Perturbation Effects in Evaluating Time Series Attributions](https://mlsanity.com/paper/2502.17022/) (2025)
- [Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions](https://mlsanity.com/paper/2310.04178/) (2023)
- [CGS-Mask: Making Time Series Predictions Intuitive for All](https://mlsanity.com/paper/2312.09513/) (2023)
- [FREQuency ATTribution: benchmarking frequency-based occlusion for time series data](https://mlsanity.com/paper/2506.18481/) (2025)
- [Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation](https://mlsanity.com/paper/2607.24608/) (2026)

## Abstract (arXiv)

In the last decade neural network have made huge impact both in industry and research due to their ability to extract meaningful features from imprecise or complex data, and by achieving super human performance in several domains. However, due to the lack of transparency the use of these networks is hampered in the areas with safety critical areas. In safety-critical areas, this is necessary by law. Recently several methods have been proposed to uncover this black box by providing interpreation of predictions made by these models. The paper focuses on time series analysis and benchmark several state-of-the-art attribution methods which compute explanations for convolutional classifiers. The presented experiments involve gradient-based and perturbation-based attribution methods. A detailed analysis shows that perturbation-based approaches are superior concerning the Sensitivity and occlusion game. These methods tend to produce explanations with higher continuity. Contrarily, the gradient-based techniques are superb in runtime and Infidelity. In addition, a validation the dependence of the methods on the trained model, feasible application domains, and individual characteristics is attached. The findings accentuate that choosing the best-suited attribution method is strongly correlated with the desired use case. Neither category of attribution methods nor a single approach has shown outstanding performance across all aspects.