Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting

TL;DR

The paper introduces TEFN, a novel architecture for long-term time series forecasting that fuses multi-source information using evidence theory, achieving high accuracy, efficiency, robustness, and interpretability.

Contribution

The paper proposes TEFN, a new backbone architecture utilizing evidence theory for multi-source information fusion in time series forecasting, enhancing accuracy and interpretability while reducing complexity.

Findings

TEFN achieves comparable accuracy to state-of-the-art methods.

TEFN maintains lower complexity and training time.

TEFN exhibits high robustness with minimal error fluctuations.

Abstract

In practical scenarios, time series forecasting necessitates not only accuracy but also efficiency. Consequently, the exploration of model architectures remains a perennially trending topic in research. To address these challenges, we propose a novel backbone architecture named Time Evidence Fusion Network (TEFN) from the perspective of information fusion. Specifically, we introduce the Basic Probability Assignment (BPA) Module based on evidence theory to capture the uncertainty of multivariate time series data from both channel and time dimensions. Additionally, we develop a novel multi-source information fusion method to effectively integrate the two distinct dimensions from BPA output, leading to improved forecasting accuracy. Lastly, we conduct extensive experiments to demonstrate that TEFN achieves performance comparable to state-of-the-art methods while maintaining significantly lower complexity and reduced training time. Also, our experiments show that TEFN exhibits high robustness, with minimal error fluctuations during hyperparameter selection. Furthermore, due to the fact that BPA is derived from fuzzy theory, TEFN offers a high degree of interpretability. Therefore, the proposed TEFN balances accuracy, efficiency, stability, and interpretability, making it a desirable solution for time series forecasting.