.png){kind=icon}
.png){kind=icon}
Return
Multi-Scale Attention Flow for Probabilistic Time Series Forecasting
.png){kind=icon}
OA
AI
S
C
K
J
P
Y
P
DOI：10.1109/TKDE.2023.3319672.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The probability prediction of multivariate time series is a notoriously challenging but practical task. On the one hand, the challenge is how to effectively capture the cross-series correlations between interacting time series, to achieve accurate distribution modeling. On the other hand, we should consider how to capture the contextual information within time series more accurately to model multivariate temporal dynamics of time series. In this work, we proposed a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF), where we combine multi-scale attention with relative position information and the multivariate data distribution is represented by the conditioned normalizing flow. Additionally, compared with autoregressive modeling methods, our model avoids the influence of cumulative error and does not increase the time complexity. Extensive experiments demonstrate that our model achieves state-of-the-art performance on many popular multivariate datasets.
Keywords:
Time series analysis
Forecasting
Predictive models
Correlation
Probabilistic logic
Data models
Task analysis
Multivariate time series
normalizing flow
multi-scale attention
generative model
Journal
IF:
10.4
Papers:
6.7K
Citations:
3.2W
Organization
Cited Papers