TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cao, Defu, Jia, Furong, Arik, Sercan O, Pfister, Tomas, Zheng, Yixiang, Ye, Wen, Liu, Yan
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914737865883648
author Cao, Defu
Jia, Furong
Arik, Sercan O
Pfister, Tomas
Zheng, Yixiang
Ye, Wen
Liu, Yan
author_facet Cao, Defu
Jia, Furong
Arik, Sercan O
Pfister, Tomas
Zheng, Yixiang
Ye, Wen
Liu, Yan
contents The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural language processing, the Generative Pre-trained Transformer (GPT) has demonstrated impressive performance via training one general-purpose model across various textual datasets. It is intriguing to explore whether GPT-type architectures can be effective for time series, capturing the intrinsic dynamic attributes and leading to significant accuracy improvements. In this paper, we propose a novel framework, TEMPO, that can effectively learn time series representations. We focus on utilizing two essential inductive biases of the time series task for pre-trained models: (i) decomposition of the complex interaction between trend, seasonal and residual components; and (ii) introducing the design of prompts to facilitate distribution adaptation in different types of time series. TEMPO expands the capability for dynamically modeling real-world temporal phenomena from data within diverse domains. Our experiments demonstrate the superior performance of TEMPO over state-of-the-art methods on zero shot setting for a number of time series benchmark datasets. This performance gain is observed not only in scenarios involving previously unseen datasets but also in scenarios with multi-modal inputs. This compelling finding highlights TEMPO's potential to constitute a foundational model-building framework.
format Preprint
id arxiv_https___arxiv_org_abs_2310_04948
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
Cao, Defu
Jia, Furong
Arik, Sercan O
Pfister, Tomas
Zheng, Yixiang
Ye, Wen
Liu, Yan
Machine Learning
Computation and Language
The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural language processing, the Generative Pre-trained Transformer (GPT) has demonstrated impressive performance via training one general-purpose model across various textual datasets. It is intriguing to explore whether GPT-type architectures can be effective for time series, capturing the intrinsic dynamic attributes and leading to significant accuracy improvements. In this paper, we propose a novel framework, TEMPO, that can effectively learn time series representations. We focus on utilizing two essential inductive biases of the time series task for pre-trained models: (i) decomposition of the complex interaction between trend, seasonal and residual components; and (ii) introducing the design of prompts to facilitate distribution adaptation in different types of time series. TEMPO expands the capability for dynamically modeling real-world temporal phenomena from data within diverse domains. Our experiments demonstrate the superior performance of TEMPO over state-of-the-art methods on zero shot setting for a number of time series benchmark datasets. This performance gain is observed not only in scenarios involving previously unseen datasets but also in scenarios with multi-modal inputs. This compelling finding highlights TEMPO's potential to constitute a foundational model-building framework.
title TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2310.04948