Explaining Time Series via Contrastive and Locally Sparse Perturbations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917576823537664 |
|---|---|
| author | Liu, Zichuan Zhang, Yingying Wang, Tianchun Wang, Zefan Luo, Dongsheng Du, Mengnan Wu, Min Wang, Yi Chen, Chunlin Fan, Lunting Wen, Qingsong |
| author_facet | Liu, Zichuan Zhang, Yingying Wang, Tianchun Wang, Zefan Luo, Dongsheng Du, Mengnan Wu, Min Wang, Yi Chen, Chunlin Fan, Lunting Wen, Qingsong |
| contents | Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns. Although previous saliency-based methods addressed the challenges, their perturbation may not alleviate the distribution shift issue, which is inevitable especially in heterogeneous samples. We present ContraLSP, a locally sparse model that introduces counterfactual samples to build uninformative perturbations but keeps distribution using contrastive learning. Furthermore, we incorporate sample-specific sparse gates to generate more binary-skewed and smooth masks, which easily integrate temporal trends and select the salient features parsimoniously. Empirical studies on both synthetic and real-world datasets show that ContraLSP outperforms state-of-the-art models, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at \url{https://github.com/zichuan-liu/ContraLSP}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08552 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explaining Time Series via Contrastive and Locally Sparse Perturbations Liu, Zichuan Zhang, Yingying Wang, Tianchun Wang, Zefan Luo, Dongsheng Du, Mengnan Wu, Min Wang, Yi Chen, Chunlin Fan, Lunting Wen, Qingsong Machine Learning Artificial Intelligence Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns. Although previous saliency-based methods addressed the challenges, their perturbation may not alleviate the distribution shift issue, which is inevitable especially in heterogeneous samples. We present ContraLSP, a locally sparse model that introduces counterfactual samples to build uninformative perturbations but keeps distribution using contrastive learning. Furthermore, we incorporate sample-specific sparse gates to generate more binary-skewed and smooth masks, which easily integrate temporal trends and select the salient features parsimoniously. Empirical studies on both synthetic and real-world datasets show that ContraLSP outperforms state-of-the-art models, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at \url{https://github.com/zichuan-liu/ContraLSP}. |
| title | Explaining Time Series via Contrastive and Locally Sparse Perturbations |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2401.08552 |