Explanation Space: A New Perspective into Time Series Interpretability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rezaei, Shahbaz, Liu, Xin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917976003837952
author Rezaei, Shahbaz
Liu, Xin
author_facet Rezaei, Shahbaz
Liu, Xin
contents Human understandable explanation of deep learning models is essential for various critical and sensitive applications. Unlike image or tabular data where the importance of each input feature (for the classifier's decision) can be directly projected into the input, time series distinguishable features (e.g. dominant frequency) are often hard to manifest in time domain for a user to easily understand. Additionally, most explanation methods require a baseline value as an indication of the absence of any feature. However, the notion of lack of feature, which is often defined as black pixels for vision tasks or zero/mean values for tabular data, is not well-defined in time series. Despite the adoption of explainable AI methods (XAI) from tabular and vision domain into time series domain, these differences limit the application of these XAI methods in practice. In this paper, we propose a simple yet effective method that allows a model originally trained on the time domain to be interpreted in other explanation spaces using existing methods. We suggest five explanation spaces, each of which can potentially alleviate these issues in certain types of time series. Our method can be easily integrated into existing platforms without any changes to trained models or XAI methods. The code will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2409_01354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Explanation Space: A New Perspective into Time Series Interpretability
Rezaei, Shahbaz
Liu, Xin
Machine Learning
Artificial Intelligence
Human understandable explanation of deep learning models is essential for various critical and sensitive applications. Unlike image or tabular data where the importance of each input feature (for the classifier's decision) can be directly projected into the input, time series distinguishable features (e.g. dominant frequency) are often hard to manifest in time domain for a user to easily understand. Additionally, most explanation methods require a baseline value as an indication of the absence of any feature. However, the notion of lack of feature, which is often defined as black pixels for vision tasks or zero/mean values for tabular data, is not well-defined in time series. Despite the adoption of explainable AI methods (XAI) from tabular and vision domain into time series domain, these differences limit the application of these XAI methods in practice. In this paper, we propose a simple yet effective method that allows a model originally trained on the time domain to be interpreted in other explanation spaces using existing methods. We suggest five explanation spaces, each of which can potentially alleviate these issues in certain types of time series. Our method can be easily integrated into existing platforms without any changes to trained models or XAI methods. The code will be released upon acceptance.
title Explanation Space: A New Perspective into Time Series Interpretability
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2409.01354