Multi-Stage Prototype Learning for Interpretable Time Series Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914540806995968 |
|---|---|
| author | Kalisetti, Bhavesh Wang, Vincent Ghosal, Gaurav R. Bijanzadeh, Maryam Abbasi-Asl, Reza |
| author_facet | Kalisetti, Bhavesh Wang, Vincent Ghosal, Gaurav R. Bijanzadeh, Maryam Abbasi-Asl, Reza |
| contents | Deep learning methods are powerful tools in classifying multivariate time series data. Despite their high performance, these methods are hard to interpret, which diminishes their applications in high-risk domains such as healthcare. In this paper, we propose a novel multi-stage prototype learning framework for multivariate time series classification. By design, our framework identifies predictive temporal patterns in individual variables as well as cross-variable patterns that are highly predictive of each class. We validate our model on one simulated and four real-world datasets and demonstrate comparable accuracy to state-of-the-art methods while providing substantially improved interpretability through explicit, hierarchical prototype-based explanations. These explanations reveal both single-variable temporal patterns as well as cross-variable interactions that are most predictive for each class, providing insights into underlying mechanisms of the predictive model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_09636 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Multi-Stage Prototype Learning for Interpretable Time Series Classification Kalisetti, Bhavesh Wang, Vincent Ghosal, Gaurav R. Bijanzadeh, Maryam Abbasi-Asl, Reza Machine Learning Deep learning methods are powerful tools in classifying multivariate time series data. Despite their high performance, these methods are hard to interpret, which diminishes their applications in high-risk domains such as healthcare. In this paper, we propose a novel multi-stage prototype learning framework for multivariate time series classification. By design, our framework identifies predictive temporal patterns in individual variables as well as cross-variable patterns that are highly predictive of each class. We validate our model on one simulated and four real-world datasets and demonstrate comparable accuracy to state-of-the-art methods while providing substantially improved interpretability through explicit, hierarchical prototype-based explanations. These explanations reveal both single-variable temporal patterns as well as cross-variable interactions that are most predictive for each class, providing insights into underlying mechanisms of the predictive model. |
| title | Multi-Stage Prototype Learning for Interpretable Time Series Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2106.09636 |