A Data-Driven Scale-Adaptive Time-Frequency Convolutional Network for Long Sequence Time-Series Forecasting

Zhiqiang Zhang

doi:10.1109/TKDE.2025.3619521

A Data-Driven Scale-Adaptive Time-Frequency Convolutional Network for Long Sequence Time-Series Forecasting

2025-10-09

0

PRE

AI

DOI：10.1109/TKDE.2025.3619521

Original

Original request for help

Save

Abstract

En 中文

Models based on Transformer variants have consistently demonstrated leading performance in long sequence time series forecasting. However, in some complex application scenarios, Transformers tend to capture low-frequency information in the data while overlooking high-frequency information, which often contains rich non-stationary features. This unbalanced feature extraction approach limits the model’s ability to effectively handle real-world time series data. To address this issue, we explicitly represent both low-frequency and high-frequency information and propose a model called STCNet, a data-driven scale-adaptive convolutional network that aims to extract diverse features and patterns from the data by learning features across different frequency bands in a balanced manner. Specifically, we propose an entropy-based adaptive wavelet basis selection algorithm, which can adaptively select appropriate wavelet bases based on the data distribution to achieve effective multi-frequency decomposition of complex time series. In addition, we designed a hierarchical scale-adaptive factor that allows for dynamic adjustment of feature weights according to different time scales through refined layered weight adjustment, significantly enhancing the model’s capability in handling non-stationary time series features. To further optimize the output features of the model, we introduce a test-time training mechanism, combined with a fast weight update strategy and a weight-sharing strategy to reduce the number of model parameters, effectively mitigating the risk of overfitting. Experimental results on nine datasets demonstrate that STCNet outperforms the current state-of-the-art models in both effectiveness and efficiency.

Keywords:

Long sequence time series forecasting

non-stationary

frequency

entropy-based

scale-adaptive

A Data-Driven Scale-Adaptive Time-Frequency Convolutional Network for Long Sequence Time-Series Forecasting

Abstract

Journal

Organization