Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913214988550144 |
|---|---|
| author | Wang, Zhengguang |
| author_facet | Wang, Zhengguang |
| contents | 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 the post-hoc interpretation methods such as back-propagation, perturbation, and approximation, my work will investigate perturbation-based sensitivity Analysis methods on modern Transformer models to benchmark their performances. Specifically, my work answers three research questions: 1) Do different sensitivity analysis (SA) methods yield comparable outputs and attribute importance rankings? 2) Using the same sensitivity analysis method, do different Deep Learning (DL) models impact the output of the sensitivity analysis? 3) How well do the results from sensitivity analysis methods align with the ground truth? |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16521 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models Wang, Zhengguang Machine Learning Artificial Intelligence 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 the post-hoc interpretation methods such as back-propagation, perturbation, and approximation, my work will investigate perturbation-based sensitivity Analysis methods on modern Transformer models to benchmark their performances. Specifically, my work answers three research questions: 1) Do different sensitivity analysis (SA) methods yield comparable outputs and attribute importance rankings? 2) Using the same sensitivity analysis method, do different Deep Learning (DL) models impact the output of the sensitivity analysis? 3) How well do the results from sensitivity analysis methods align with the ground truth? |
| title | Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2401.16521 |