We propose LaST, which, based on variational inference, aims to disentangle the seasonal-trend representations in the latent space.
Oct 31, 2022 · The paper presents an approach for learning latent season-trend based representations for time-series forecasting, based on variational ...
We propose LaST, a novel latent seasonal-trend representations learning framework, which encodes input as disentangled seasonal-trend representations and ...
LaST: Learning Latent Seasonal-Trend Representations for Time Series Forecasting. In this repository, we provide the original PyTorch implementation of LaST ...
This work proposes LaST, which, based on variational inference, aims to disentangle the seasonal-trend representations in the latent space and achieves ...
Apr 3, 2024 · Extensive experiments prove that LaST achieves state-of-the-art performance on time series forecasting task against the most advanced ...
Apr 4, 2023 · This paper aims to infer some representations that describe the seasonal (periodic variation) and trend components of time series.
People also ask
How do you identify trends and seasonality in a time series?
What is Arima model for time series forecasting?
How to deal with seasonality in time series?
Which of the following forecasting methods is appropriate for time series data that exhibits seasonality?
Jan 5, 2024 · I am looking for the best unsupervised / self-supervised encoding techniques that learn useful latent feature representations.
We show via a causal perspective, the benefits of learning disentangled seasonal-trend rep- resentations for time series forecasting via contrastive learning. 2 ...
Learning latent seasonal-trend representations for time series forecasting. Z Wang, X Xu, W Zhang, G Trajcevski, T Zhong, F Zhou. Advances in Neural ...