Enhancing few-shot time series forecasting with LLM-guided diffusion

TL;DR

This paper introduces LTSM-DIFF, a novel framework combining large language models and diffusion techniques to improve few-shot time series forecasting, achieving state-of-the-art results especially when data is scarce.

Contribution

The paper proposes a new method integrating language models with diffusion processes for enhanced few-shot time series forecasting, a novel approach in the field.

Findings

Achieves state-of-the-art performance in data-rich scenarios.

Significantly improves forecasting accuracy in few-shot settings.

Demonstrates robustness and generalization across diverse benchmarks.

Abstract

Time series forecasting in specialized domains is often constrained by limited data availability, where conventional models typically require large-scale datasets to effectively capture underlying temporal dynamics. To tackle this few-shot challenge, we propose LTSM-DIFF (Large-scale Temporal Sequential Memory with Diffusion), a novel learning framework that integrates the expressive power of large language models with the generative capability of diffusion models. Specifically, the LTSM module is fine-tuned and employed as a temporal memory mechanism, extracting rich sequential representations even under data-scarce conditions. These representations are then utilized as conditional guidance for a joint probability diffusion process, enabling refined modeling of complex temporal patterns. This design allows knowledge transfer from the language domain to time series tasks, substantially enhancing both generalization and robustness. Extensive experiments across diverse benchmarks demonstrate that LTSM-DIFF consistently achieves state-of-the-art performance in data-rich scenarios, while also delivering significant improvements in few-shot forecasting. Our work establishes a new paradigm for time series analysis under data scarcity.