Overview

Time Series Transformers apply attention to ordered observations, helping model patterns over time and relationships among multiple variables for forecasting, classification, and anomaly detection. Common approaches use patches, separate temporal and channel-wise attention, or add frequency, spatial, and domain-specific structure; pretrained foundation models also aim to transfer across datasets and tasks. Work increasingly addresses long and irregular sequences, uncertainty, and efficient inference through sparse attention, adaptive tokenization, and hybrid architectures. A central tension is that added complexity does not guarantee better accuracy or generalization: performance depends on the data, forecast horizon, preprocessing, and evaluation, and simple statistical or smaller neural models can remain competitive.

Latest papers

CardsList

151 papers11 papers in the last four weeks, down 21% on the four weeks before. 0.1% of all new papers.

  1. Embedded Decomposed Transformer for explainable multivariate time series forecasting

    Dec 16, 2024Sanjay Chakraborty, Ibrahim Delibasoglu, Fredrik HeintzMultivariate Time Series ForecastingTime Series Transformers