TimeX++: Learning Time-Series Explanations with Information Bottleneck
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_ | 1866910448429826048 |
|---|---|
| author | Liu, Zichuan Wang, Tianchun Shi, Jimeng Zheng, Xu Chen, Zhuomin Song, Lei Dong, Wenqian Obeysekera, Jayantha Shirani, Farhad Luo, Dongsheng |
| author_facet | Liu, Zichuan Wang, Tianchun Shi, Jimeng Zheng, Xu Chen, Zhuomin Song, Lei Dong, Wenqian Obeysekera, Jayantha Shirani, Farhad Luo, Dongsheng |
| contents | Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an information theoretic perspective and show that most existing measures of explainability may suffer from trivial solutions and distributional shift issues. To address these issues, we introduce a simple yet practical objective function for time series explainable learning. The design of the objective function builds upon the principle of information bottleneck (IB), and modifies the IB objective function to avoid trivial solutions and distributional shift issues. We further present TimeX++, a novel explanation framework that leverages a parametric network to produce explanation-embedded instances that are both in-distributed and label-preserving. We evaluate TimeX++ on both synthetic and real-world datasets comparing its performance against leading baselines, and validate its practical efficacy through case studies in a real-world environmental application. Quantitative and qualitative evaluations show that TimeX++ outperforms baselines across all datasets, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at \url{https://github.com/zichuan-liu/TimeXplusplus}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09308 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TimeX++: Learning Time-Series Explanations with Information Bottleneck Liu, Zichuan Wang, Tianchun Shi, Jimeng Zheng, Xu Chen, Zhuomin Song, Lei Dong, Wenqian Obeysekera, Jayantha Shirani, Farhad Luo, Dongsheng Machine Learning Artificial Intelligence Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an information theoretic perspective and show that most existing measures of explainability may suffer from trivial solutions and distributional shift issues. To address these issues, we introduce a simple yet practical objective function for time series explainable learning. The design of the objective function builds upon the principle of information bottleneck (IB), and modifies the IB objective function to avoid trivial solutions and distributional shift issues. We further present TimeX++, a novel explanation framework that leverages a parametric network to produce explanation-embedded instances that are both in-distributed and label-preserving. We evaluate TimeX++ on both synthetic and real-world datasets comparing its performance against leading baselines, and validate its practical efficacy through case studies in a real-world environmental application. Quantitative and qualitative evaluations show that TimeX++ outperforms baselines across all datasets, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at \url{https://github.com/zichuan-liu/TimeXplusplus}. |
| title | TimeX++: Learning Time-Series Explanations with Information Bottleneck |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2405.09308 |