DeepAI AI Chat
Log In Sign Up

CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting

by   Gerald Woo, et al.

Deep learning has been actively studied for time series forecasting, and the mainstream paradigm is based on the end-to-end training of neural network architectures, ranging from classical LSTM/RNNs to more recent TCNs and Transformers. Motivated by the recent success of representation learning in computer vision and natural language processing, we argue that a more promising paradigm for time series forecasting, is to first learn disentangled feature representations, followed by a simple regression fine-tuning step – we justify such a paradigm from a causal perspective. Following this principle, we propose a new time series representation learning framework for time series forecasting named CoST, which applies contrastive learning methods to learn disentangled seasonal-trend representations. CoST comprises both time domain and frequency domain contrastive losses to learn discriminative trend and seasonal representations, respectively. Extensive experiments on real-world datasets show that CoST consistently outperforms the state-of-the-art methods by a considerable margin, achieving a 21.3% improvement in MSE on multivariate benchmarks. It is also robust to various choices of backbone encoders, as well as downstream regressors.


page 1

page 2

page 3

page 4


Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting

Time series forecasting is a significant problem in many applications, e...

PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting

This paper studies the time series forecasting problem from a whole new ...

Deep Temporal Contrastive Clustering

Recently the deep learning has shown its advantage in representation lea...

Time Series Contrastive Learning with Information-Aware Augmentations

Various contrastive learning approaches have been proposed in recent yea...

Learning Sparse and Continuous Graph Structures for Multivariate Time Series Forecasting

Accurate forecasting of multivariate time series is an extensively studi...

DeepTIMe: Deep Time-Index Meta-Learning for Non-Stationary Time-Series Forecasting

Deep learning has been actively applied to time-series forecasting, lead...

Learning Disentangled Representations for Time Series

Time-series representation learning is a fundamental task for time-serie...