QuLTSF: Long-Term Time Series Forecasting with Quantum Machine Learning

2024-12-18

arXiv.org

AI Summary

Long-term time series forecasting (LTSF) is critical in domains such as meteorology, finance, and public health; however, existing Transformer-based models suffer from high computational complexity and inefficiency, while simple linear models often achieve competitive performance. To address this, we propose QuLTSF—the first quantum-classical hybrid model for multivariate LTSF—introducing parameterized quantum circuits into the LTSF framework for the first time. QuLTSF integrates classical linear mappings with end-to-end differentiable training, eliminating architectural redundancy to enable lightweight and efficient modeling. Evaluated on a standard weather dataset, QuLTSF significantly outperforms state-of-the-art classical linear baselines, reducing MSE and MAE by 12.7% and 9.3%, respectively. This work empirically validates the effectiveness of quantum enhancement in LTSF and establishes a novel paradigm for resource-constrained time series modeling.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Long-term time series forecasting (LTSF) involves predicting a large number of future values of a time series based on the past values and is an essential task in a wide range of domains including weather forecasting, stock market analysis, disease outbreak prediction. Over the decades LTSF algorithms have transitioned from statistical models to deep learning models like transformer models. Despite the complex architecture of transformer based LTSF models `Are Transformers Effective for Time Series Forecasting? (Zeng et al., 2023)' showed that simple linear models can outperform the state-of-the-art transformer based LTSF models. Recently, quantum machine learning (QML) is evolving as a domain to enhance the capabilities of classical machine learning models. In this paper we initiate the application of QML to LTSF problems by proposing QuLTSF, a simple hybrid QML model for multivariate LTSF. Through extensive experiments on a widely used weather dataset we show the advantages of QuLTSF over the state-of-the-art classical linear models, in terms of reduced mean squared error and mean absolute error.

Problem

• Long-term time series forecasting using quantum machine learning.
• Comparison of QuLTSF with classical linear models for accuracy.
• Application of QuLTSF to improve weather forecasting predictions.

Innovation

• Hybrid quantum-classical machine learning model
• Applies quantum machine learning to time series
• Outperforms classical linear models in accuracy