Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting
This work addresses the need for accurate and efficient forecasting models in practical time series applications, representing an incremental improvement with a focus on balancing multiple performance metrics.
The paper tackles long-term time series forecasting by proposing the Time Evidence Fusion Network (TEFN), which uses evidence theory to capture uncertainty and fuse multi-source information, achieving performance comparable to state-of-the-art methods with significantly lower complexity and training time.
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.