Transfer Learning with Foundational Models for Time Series Forecasting using Low-Rank Adaptations

TL;DR

This paper introduces LLIAM, a simple transfer learning method using Low-Rank Adaptations of foundational models, to improve time series forecasting with minimal fine-tuning, achieving competitive results across various datasets.

Contribution

The study proposes LLIAM, a novel adaptation technique for foundational models in time series forecasting, demonstrating its effectiveness and generalization capabilities with minimal modifications.

Findings

LLIAM outperforms several state-of-the-art deep learning models.

The approach generalizes well to unseen domains.

It achieves competitive results with less computational cost.

Abstract

Foundational Models are an emerging widely used technique of GenAI. These models are distinguished by their scalability and the ease with which they can be adapted through the exploitation of Transfer Learning. The availability of high computational power and large datasets have supported their development, achieving a high generalization capacity due to the enormous and heterogeneous amounts of data used in their initial training. These characteristics contribute to a solid base that can be adapted or adjusted to a wide range of tasks, increasing their applicability. This study proposes the methodology LLIAM, a straightforward adaptation of a kind of FM, Large Language Models, for the Time Series Forecasting task. An adequate time-series prompting schema and Low-Rank Adaptations are used to enhance the knowledge of the model with diverse time series datasets, known as the fine-tuning phase. A study divided in two stages has been performed for evaluating the effectiveness of the proposed methodology. Initially, a comparison was made between the performance of LLIAM and different state-of-the-art DL algorithms, including Recurrent Neural Networks and Temporal Convolutional Networks, as well as a LLM-based method, TimeLLM. Following this, a zero-shot study is presented in order to evaluate the generalization capacity of the proposed methodology with time series datasets from unknown domains not considered in the model training. The outcomes of this investigation demonstrate the efficacy of LLIAM, highlighting that this straightforward and general approach can attain competent results without the necessity for applying complex modifications. This work also encourages the use of available resources (such as these pre-trained models) and efficient fine-tuning techniques to avoid unnecessary and costly training, narrowing the gap between the goals of traditional AI and Green AI.