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.
翻译:最近对TRRANSORMER的各种修改被用于解决时间序列预测问题。 我们建议查询选择器(Query Shoppleor ) — — 一种高效的确定性算法,用于稀疏关注矩阵。 实验显示它取得了ETT数据集的最新结果 。