MFF-FTNet: Multi-scale Feature Fusion across Frequency and Temporal Domains for Time Series Forecasting

TL;DR

MFF-FTNet is a new deep learning framework that combines multi-scale feature extraction and contrastive learning across frequency and time domains to improve the accuracy and robustness of time series forecasting, especially in noisy and sparse data conditions.

Contribution

It introduces an adaptive noise augmentation strategy and a dual-module architecture for spectral and temporal feature fusion, advancing multi-scale time series modeling.

Findings

Achieves 7.7% lower MSE on multivariate datasets

Outperforms state-of-the-art models in accuracy

Effectively handles noise and data sparsity

Abstract

Time series forecasting is crucial in many fields, yet current deep learning models struggle with noise, data sparsity, and capturing complex multi-scale patterns. This paper presents MFF-FTNet, a novel framework addressing these challenges by combining contrastive learning with multi-scale feature extraction across both frequency and time domains. MFF-FTNet introduces an adaptive noise augmentation strategy that adjusts scaling and shifting factors based on the statistical properties of the original time series data, enhancing model resilience to noise. The architecture is built around two complementary modules: a Frequency-Aware Contrastive Module (FACM) that refines spectral representations through frequency selection and contrastive learning, and a Complementary Time Domain Contrastive Module (CTCM) that captures both short- and long-term dependencies using multi-scale convolutions and feature fusion. A unified feature representation strategy enables robust contrastive learning across domains, creating an enriched framework for accurate forecasting. Extensive experiments on five real-world datasets demonstrate that MFF-FTNet significantly outperforms state-of-the-art models, achieving a 7.7% MSE improvement on multivariate tasks. These findings underscore MFF-FTNet's effectiveness in modeling complex temporal patterns and managing noise and sparsity, providing a comprehensive solution for both long- and short-term forecasting.