Treating Brain-inspired Memories as Priors for Diffusion Model to Forecast Multivariate Time Series
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912047974842368 |
|---|---|
| author | Wang, Muyao Chen, Wenchao Duan, Zhibin Chen, Bo |
| author_facet | Wang, Muyao Chen, Wenchao Duan, Zhibin Chen, Bo |
| contents | Forecasting Multivariate Time Series (MTS) involves significant challenges in various application domains. One immediate challenge is modeling temporal patterns with the finite length of the input. These temporal patterns usually involve periodic and sudden events that recur across different channels. To better capture temporal patterns, we get inspiration from humans' memory mechanisms and propose a channel-shared, brain-inspired memory module for MTS. Specifically, brain-inspired memory comprises semantic and episodic memory, where the former is used to capture general patterns, such as periodic events, and the latter is employed to capture special patterns, such as sudden events, respectively. Meanwhile, we design corresponding recall and update mechanisms to better utilize these patterns. Furthermore, acknowledging the capacity of diffusion models to leverage memory as a prior, we present a brain-inspired memory-augmented diffusion model. This innovative model retrieves relevant memories for different channels, utilizing them as distinct priors for MTS predictions. This incorporation significantly enhances the accuracy and robustness of predictions. Experimental results on eight datasets consistently validate the superiority of our approach in capturing and leveraging diverse recurrent temporal patterns across different channels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18491 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Treating Brain-inspired Memories as Priors for Diffusion Model to Forecast Multivariate Time Series Wang, Muyao Chen, Wenchao Duan, Zhibin Chen, Bo Machine Learning Forecasting Multivariate Time Series (MTS) involves significant challenges in various application domains. One immediate challenge is modeling temporal patterns with the finite length of the input. These temporal patterns usually involve periodic and sudden events that recur across different channels. To better capture temporal patterns, we get inspiration from humans' memory mechanisms and propose a channel-shared, brain-inspired memory module for MTS. Specifically, brain-inspired memory comprises semantic and episodic memory, where the former is used to capture general patterns, such as periodic events, and the latter is employed to capture special patterns, such as sudden events, respectively. Meanwhile, we design corresponding recall and update mechanisms to better utilize these patterns. Furthermore, acknowledging the capacity of diffusion models to leverage memory as a prior, we present a brain-inspired memory-augmented diffusion model. This innovative model retrieves relevant memories for different channels, utilizing them as distinct priors for MTS predictions. This incorporation significantly enhances the accuracy and robustness of predictions. Experimental results on eight datasets consistently validate the superiority of our approach in capturing and leveraging diverse recurrent temporal patterns across different channels. |
| title | Treating Brain-inspired Memories as Priors for Diffusion Model to Forecast Multivariate Time Series |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.18491 |