Interpreting Time Series Transformer Models and Sensitivity Analysis of Population Age Groups to COVID-19 Infections

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Islam, Md Khairul, Valentine, Tyler, Sue, Timothy Joowon, Karmacharya, Ayush, Benham, Luke Neil, Wang, Zhengguang, Kim, Kingsley, Fox, Judy
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916108305432576
author Islam, Md Khairul
Valentine, Tyler
Sue, Timothy Joowon
Karmacharya, Ayush
Benham, Luke Neil
Wang, Zhengguang
Kim, Kingsley
Fox, Judy
author_facet Islam, Md Khairul
Valentine, Tyler
Sue, Timothy Joowon
Karmacharya, Ayush
Benham, Luke Neil
Wang, Zhengguang
Kim, Kingsley
Fox, Judy
contents Interpreting deep learning time series models is crucial in understanding the model's behavior and learning patterns from raw data for real-time decision-making. However, the complexity inherent in transformer-based time series models poses challenges in explaining the impact of individual features on predictions. In this study, we leverage recent local interpretation methods to interpret state-of-the-art time series models. To use real-world datasets, we collected three years of daily case data for 3,142 US counties. Firstly, we compare six transformer-based models and choose the best prediction model for COVID-19 infection. Using 13 input features from the last two weeks, we can predict the cases for the next two weeks. Secondly, we present an innovative way to evaluate the prediction sensitivity to 8 population age groups over highly dynamic multivariate infection data. Thirdly, we compare our proposed perturbation-based interpretation method with related work, including a total of eight local interpretation methods. Finally, we apply our framework to traffic and electricity datasets, demonstrating that our approach is generic and can be applied to other time-series domains.
format Preprint
id arxiv_https___arxiv_org_abs_2401_15119
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interpreting Time Series Transformer Models and Sensitivity Analysis of Population Age Groups to COVID-19 Infections
Islam, Md Khairul
Valentine, Tyler
Sue, Timothy Joowon
Karmacharya, Ayush
Benham, Luke Neil
Wang, Zhengguang
Kim, Kingsley
Fox, Judy
Machine Learning
Artificial Intelligence
Populations and Evolution
Interpreting deep learning time series models is crucial in understanding the model's behavior and learning patterns from raw data for real-time decision-making. However, the complexity inherent in transformer-based time series models poses challenges in explaining the impact of individual features on predictions. In this study, we leverage recent local interpretation methods to interpret state-of-the-art time series models. To use real-world datasets, we collected three years of daily case data for 3,142 US counties. Firstly, we compare six transformer-based models and choose the best prediction model for COVID-19 infection. Using 13 input features from the last two weeks, we can predict the cases for the next two weeks. Secondly, we present an innovative way to evaluate the prediction sensitivity to 8 population age groups over highly dynamic multivariate infection data. Thirdly, we compare our proposed perturbation-based interpretation method with related work, including a total of eight local interpretation methods. Finally, we apply our framework to traffic and electricity datasets, demonstrating that our approach is generic and can be applied to other time-series domains.
title Interpreting Time Series Transformer Models and Sensitivity Analysis of Population Age Groups to COVID-19 Infections
topic Machine Learning
Artificial Intelligence
Populations and Evolution
url https://arxiv.org/abs/2401.15119