TS-HTFA: Advancing Time Series Forecasting via Hierarchical Text-Free Alignment with Large Language Models

TL;DR

TS-HTFA is a novel hierarchical alignment method that enhances time series forecasting using large language models without relying on paired text data, achieving state-of-the-art results.

Contribution

It introduces a text-free hierarchical alignment approach that fully exploits LLMs for time series forecasting, overcoming reliance on paired text data and addressing modality gaps.

Findings

Achieves state-of-the-art forecasting accuracy on multiple benchmarks.

Effectively eliminates dependence on paired text data.

Improves model generalization across diverse time-series datasets.

Abstract

Given the significant potential of large language models (LLMs) in sequence modeling, emerging studies have begun applying them to time-series forecasting. Despite notable progress, existing methods still face two critical challenges: 1) their reliance on large amounts of paired text data, limiting the model applicability, and 2) a substantial modality gap between text and time series, leading to insufficient alignment and suboptimal performance. In this paper, we introduce \textbf{H}ierarchical \textbf{T}ext-\textbf{F}ree \textbf{A}lignment (\textbf{TS-HTFA}), a novel method that leverages hierarchical alignment to fully exploit the representation capacity of LLMs while eliminating the dependence on text data. Specifically, we replace paired text data with adaptive virtual text based on QR decomposition word embeddings and learnable prompt. Furthermore, we establish comprehensive cross-modal alignment at three levels: input, feature, and output. Extensive experiments on multiple time-series benchmarks demonstrate that HTFA achieves state-of-the-art performance, significantly improving prediction accuracy and generalization.