Timer-XL: Long-Context Transformers for Unified Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yong, Qin, Guo, Huang, Xiangdong, Wang, Jianmin, Long, Mingsheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917941738471424
author Liu, Yong
Qin, Guo
Huang, Xiangdong
Wang, Jianmin
Long, Mingsheng
author_facet Liu, Yong
Qin, Guo
Huang, Xiangdong
Wang, Jianmin
Long, Mingsheng
contents We present Timer-XL, a causal Transformer for unified time series forecasting. To uniformly predict multidimensional time series, we generalize next token prediction, predominantly adopted for 1D token sequences, to multivariate next token prediction. The paradigm formulates various forecasting tasks as a long-context prediction problem. We opt for decoder-only Transformers that capture causal dependencies from varying-length contexts for unified forecasting, making predictions on non-stationary univariate time series, multivariate series with complicated dynamics and correlations, as well as covariate-informed contexts that include exogenous variables. Technically, we propose a universal TimeAttention to capture fine-grained intra- and inter-series dependencies of flattened time series tokens (patches), which is further enhanced by deft position embedding for temporal causality and variable equivalence. Timer-XL achieves state-of-the-art performance across task-specific forecasting benchmarks through a unified approach. Based on large-scale pre-training, Timer-XL achieves state-of-the-art zero-shot performance, making it a promising architecture for pre-trained time series models. Code is available at this repository: https://github.com/thuml/Timer-XL.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04803
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
Liu, Yong
Qin, Guo
Huang, Xiangdong
Wang, Jianmin
Long, Mingsheng
Machine Learning
We present Timer-XL, a causal Transformer for unified time series forecasting. To uniformly predict multidimensional time series, we generalize next token prediction, predominantly adopted for 1D token sequences, to multivariate next token prediction. The paradigm formulates various forecasting tasks as a long-context prediction problem. We opt for decoder-only Transformers that capture causal dependencies from varying-length contexts for unified forecasting, making predictions on non-stationary univariate time series, multivariate series with complicated dynamics and correlations, as well as covariate-informed contexts that include exogenous variables. Technically, we propose a universal TimeAttention to capture fine-grained intra- and inter-series dependencies of flattened time series tokens (patches), which is further enhanced by deft position embedding for temporal causality and variable equivalence. Timer-XL achieves state-of-the-art performance across task-specific forecasting benchmarks through a unified approach. Based on large-scale pre-training, Timer-XL achieves state-of-the-art zero-shot performance, making it a promising architecture for pre-trained time series models. Code is available at this repository: https://github.com/thuml/Timer-XL.
title Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2410.04803