TSLANet: Rethinking Transformers for Time Series Representation Learning

arXiv:2404.08472v1 Announce Type: new
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 …

arxiv cs.lg representation representation learning series stat.ml time series transformers type