Document Type
Conference Proceeding
Publication Date
2024
Abstract
The high-resolution time series classification problem is essential due to the increasing availability of detailed temporal data in various domains. To tackle this challenge effectively, it is imperative that the state-of-theart attention model is scalable to accommodate the growing sequence lengths typically encountered in highresolution time series data, while also demonstrating robustness in handling the inherent noise prevalent in such datasets. To address this, we propose to hierarchically encode the long time series into multiple levels based on the interaction ranges. By capturing relationships at different levels, we can build more robust, expressive, and efficient models that are capable of capturing both short-term fluctuations and long-term trends in the data. We then propose a new time series transformer backbone (KronTime) by introducing Kronecker-decomposed attention to process such multilevel time series, which sequentially calculates attention from the lower level to the upper level. Experiments on four long time series datasets demonstrate superior classification results with improved efficiency compared to baseline methods.
Recommended Citation
Feng, Aosong, Jialin Chen, Juan Garza, Brooklyn Berry, Francisco Salazar, Yifeng Gao, Rex Ying, and Leandros Tassiulas. "Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition." arXiv preprint arXiv:2403.04882 (2024).