Time-Prompt: Integrated Heterogeneous Prompts for Unlocking LLMs in Time Series Forecasting

TL;DR

Time-Prompt introduces a novel framework that leverages integrated heterogeneous prompts to activate large language models for improved long-term time series forecasting, demonstrating effectiveness across multiple datasets.

Contribution

The paper proposes a unified prompt paradigm with learnable and textual prompts, along with a semantic space embedding and cross-modal alignment for enhanced LLM understanding in time series forecasting.

Findings

Effective on 6 public datasets and 3 carbon emission datasets.

Outperforms existing methods in long-term forecasting accuracy.

Provides a new approach for integrating LLMs into time series tasks.

Abstract

Time series forecasting aims to model temporal dependencies among variables for future state inference, holding significant importance and widespread applications in real-world scenarios. Although deep learning-based methods have achieved remarkable progress, they still exhibit suboptimal performance in long-term forecasting. Recent research demonstrates that large language models (LLMs) achieve promising performance in time series forecasting, but this progress is still met with skepticism about whether LLMs are truly useful for this task. To address this, we propose Time-Prompt, a framework for activating LLMs for time series forecasting. Specifically, we first construct a unified prompt paradigm with learnable soft prompts to guide the LLM's behavior and textualized hard prompts to enhance the time series representations. Second, to enhance LLM' comprehensive understanding of the forecasting task, we design a semantic space embedding and cross-modal alignment module to achieve fusion of temporal and textual data. Finally, we efficiently fine-tune the LLM's parameters using time series data. Furthermore, we focus on carbon emissions, aiming to provide a modest contribution to global carbon neutrality. Comprehensive evaluations on 6 public datasets and 3 carbon emission datasets demonstrate that Time-Prompt is a powerful framework for time series forecasting.