WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910864724983808 |
|---|---|
| author | Islam, Md. Khairul Fox, Judy |
| author_facet | Islam, Md. Khairul Fox, Judy |
| contents | 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 focusing mostly on classification tasks, evaluating using custom baseline models instead of the latest time series models, using simple synthetic datasets, and requiring training another model. We introduce a novel interpretation method, \textit{Windowed Temporal Saliency Rescaling (WinTSR)} addressing these limitations. WinTSR explicitly captures temporal dependencies among the past time steps and efficiently scales the feature importance with this time importance. We benchmark WinTSR against 10 recent interpretation techniques with 5 state-of-the-art deep-learning models of different architectures, including a time series foundation model. We use 3 real-world datasets for both time-series classification and regression. Our comprehensive analysis shows that WinTSR significantly outperforms other local interpretation methods in overall performance. Finally, we provide a novel, open-source framework to interpret the latest time series transformers and foundation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04532 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Islam, Md. Khairul Fox, Judy Machine Learning Artificial Intelligence 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 focusing mostly on classification tasks, evaluating using custom baseline models instead of the latest time series models, using simple synthetic datasets, and requiring training another model. We introduce a novel interpretation method, \textit{Windowed Temporal Saliency Rescaling (WinTSR)} addressing these limitations. WinTSR explicitly captures temporal dependencies among the past time steps and efficiently scales the feature importance with this time importance. We benchmark WinTSR against 10 recent interpretation techniques with 5 state-of-the-art deep-learning models of different architectures, including a time series foundation model. We use 3 real-world datasets for both time-series classification and regression. Our comprehensive analysis shows that WinTSR significantly outperforms other local interpretation methods in overall performance. Finally, we provide a novel, open-source framework to interpret the latest time series transformers and foundation models. |
| title | WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.04532 |