paper-with-me

홈 › Papers

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

2024-01-26 · Md Khairul Islam, Tyler Valentine, Timothy Joowon Sue, Ayush Karmacharya, Luke Neil Benham, Zhengguang Wang, Kingsley Kim, Judy Fox

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.

📄 PDF Abstract BibTeX arXiv:2401.15119

Code (1)

uva-mlsys/covid-19-age-groups 공식 구현 pytorch

Tasks

Decision MakingSensitivityTime Series

Similar Papers 제목 키워드 기반

Interpreting County Level COVID-19 Infection and Feature Sensitivity using Deep Learning Time Series Models

2022-10-06 · Md Khairul Islam, Di Zhu, Yingzheng Liu, Andrej Erkelens 외

Interpretable machine learning plays a key role in healthcare because it is challenging in understanding feature importance in deep learning model predictions. We propose a novel framework that uses deep learning to stud…

Deep LearningFeature ImportanceInterpretable Machine LearningPrediction+3

Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models

2024-01-29 · Zhengguang Wang

This work undertakes studies to evaluate Interpretability Methods for Time-Series Deep Learning. Sensitivity analysis assesses how input changes affect the output, constituting a key component of interpretation. Among th…

AttributeDeep LearningSensitivityTime Series

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models

2024-12-05 · Md. Khairul Islam, Judy Fox

Interpreting complex time series forecasting models is challenging due to the temporal dependencies between time steps and the dynamic relevance of input features over time. Existing interpretation methods are limited by…

Feature ImportanceTime SeriesTime Series ClassificationTime Series Forecasting

Generalizable autoregressive modeling of time series through functional narratives

2024-10-10 · Ran Liu, Wenrui Ma, Ellen Zippi, Hadi Pouransari 외

Time series data are inherently functions of time, yet current transformers often learn time series by modeling them as mere concatenations of time periods, overlooking their functional properties. In this work, we propo…

Time SeriesTime Series Analysis

Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias

2020-04-26 · Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian 외

Common methods for interpreting neural models in natural language processing typically examine either their structure or their behavior, but not both. We propose a methodology grounded in the theory of causal mediation a…