TSLANet: Rethinking Transformers for Time Series Representation Learning
This addresses the problem of noise sensitivity and computational inefficiency in time series analysis for researchers and practitioners, though it appears incremental as it builds on existing Transformer and convolutional approaches.
The paper tackled the challenge of modeling time series data with long and short-range dependencies by introducing TSLANet, a universal convolutional model that outperformed state-of-the-art models in classification, forecasting, and anomaly detection tasks.
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.