Long-term series forecasting with Query Selector -- efficient model of sparse attention

Jacek Klimek, Jakub Klimek, Witold Kraskiewicz, Mateusz Topolewski

Various modifications of TRANSFORMER were recently used to solve time-series forecasting problem. We propose Query Selector - an efficient, deterministic algorithm for sparse attention matrix. Experiments show it achieves state-of-the art results on ETT data set.

Knowledge Graph



Sign up or login to leave a comment