AdaWaveNet: Adaptive Wavelet Network for Time Series Analysis

TL;DR

AdaWaveNet introduces an adaptive wavelet-based neural network that effectively analyzes non-stationary time series data across multiple tasks, outperforming existing methods in forecasting, imputation, and super-resolution.

Contribution

It proposes a novel adaptive wavelet transformation mechanism within a neural network for better handling of non-stationary time series data.

Findings

Outperforms existing methods in forecasting, imputation, and super-resolution tasks.

Demonstrates robustness and flexibility in analyzing diverse real-world datasets.

Effective in capturing multi-scale temporal dynamics in non-stationary data.

Abstract

Time series data analysis is a critical component in various domains such as finance, healthcare, and meteorology. Despite the progress in deep learning for time series analysis, there remains a challenge in addressing the non-stationary nature of time series data. Traditional models, which are built on the assumption of constant statistical properties over time, often struggle to capture the temporal dynamics in realistic time series, resulting in bias and error in time series analysis. This paper introduces the Adaptive Wavelet Network (AdaWaveNet), a novel approach that employs Adaptive Wavelet Transformation for multi-scale analysis of non-stationary time series data. AdaWaveNet designed a lifting scheme-based wavelet decomposition and construction mechanism for adaptive and learnable wavelet transforms, which offers enhanced flexibility and robustness in analysis. We conduct extensive experiments on 10 datasets across 3 different tasks, including forecasting, imputation, and a newly established super-resolution task. The evaluations demonstrate the effectiveness of AdaWaveNet over existing methods in all three tasks, which illustrates its potential in various real-world applications.