DeepAI
Log In Sign Up

ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models

06/18/2021
by   Tijin Yan, et al.
0

Multivariate time series prediction has attracted a lot of attention because of its wide applications such as intelligence transportation, AIOps. Generative models have achieved impressive results in time series modeling because they can model data distribution and take noise into consideration. However, many existing works can not be widely used because of the constraints of functional form of generative models or the sensitivity to hyperparameters. In this paper, we propose ScoreGrad, a multivariate probabilistic time series forecasting framework based on continuous energy-based generative models. ScoreGrad is composed of time series feature extraction module and conditional stochastic differential equation based score matching module. The prediction can be achieved by iteratively solving reverse-time SDE. To the best of our knowledge, ScoreGrad is the first continuous energy based generative model used for time series forecasting. Furthermore, ScoreGrad achieves state-of-the-art results on six real-world datasets. The impact of hyperparameters and sampler types on the performance are also explored. Code is available at https://github.com/yantijin/ScoreGradPred.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 6

page 7

page 10

page 11

07/22/2022

Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect

How to handle time features shall be the core question of any time serie...
08/19/2022

Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer

A reliable and efficient representation of multivariate time series is c...
10/14/2022

Quantifying Quality of Class-Conditional Generative Models in Time-Series Domain

Generative models are designed to address the data scarcity problem. Eve...
11/04/2022

Modeling Temporal Data as Continuous Functions with Process Diffusion

Temporal data like time series are often observed at irregular intervals...
07/07/2020

Superiority of Simplicity: A Lightweight Model for Network Device Workload Prediction

The rapid growth and distribution of IT systems increases their complexi...
03/11/2022

Dual reparametrized Variational Generative Model for Time-Series Forecasting

This paper propose DualVDT, a generative model for Time-series forecasti...
02/21/2020

A copula-based time series model for global horizontal irradiation

The increasing importance of solar power for electricity generation lead...