TSLANet: Rethinking Transformers for Time Series Representation Learning

TL;DR

TSLANet is a novel lightweight convolutional model that combines spectral analysis and self-supervised learning to effectively capture complex time series patterns, outperforming transformer-based models in various tasks.

Contribution

The paper introduces TSLANet, a universal convolutional network with adaptive spectral and interactive blocks, enhancing time series representation learning with improved noise robustness and efficiency.

Findings

Outperforms state-of-the-art models in classification, forecasting, and anomaly detection.

Demonstrates robustness across different noise levels and data sizes.

Effective in capturing both long-term and short-term dependencies.

Abstract

Time series data, characterized by its intrinsic long and short-range dependencies, poses a unique challenge across analytical applications. While Transformer-based models excel at capturing long-range dependencies, they face limitations in noise sensitivity, computational efficiency, and overfitting with smaller datasets. In response, we introduce a novel Time Series Lightweight Adaptive Network (TSLANet), as a universal convolutional model for diverse time series tasks. Specifically, we propose an Adaptive Spectral Block, harnessing Fourier analysis to enhance feature representation and to capture both long-term and short-term interactions while mitigating noise via adaptive thresholding. Additionally, we introduce an Interactive Convolution Block and leverage self-supervised learning to refine the capacity of TSLANet for decoding complex temporal patterns and improve its robustness on different datasets. Our comprehensive experiments demonstrate that TSLANet outperforms state-of-the-art models in various tasks spanning classification, forecasting, and anomaly detection, showcasing its resilience and adaptability across a spectrum of noise levels and data sizes. The code is available at https://github.com/emadeldeen24/TSLANet.