Long-term series forecasting with Query Selector -- efficient model of sparse attention
MORAI；Nicholas Copernicus University（尼古拉斯·哥白尼大学）
英文摘要：
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, Helpdesk and BPI'12 datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
