Performance of AUBER and its variants.
收藏数据链接:
官方服务:
资源简介:
Comparison of AUBER with four variants: AUBER-Query, AUBER-Key, AUBER-L2, and AUBER-Reverse on four GLUE datasets to demonstrate the effectiveness of various ways to calculate the initial state. AUBER-Query and AUBER-Key use the query and key matrices respectively, and AUBER-L2 uses the L2 norm of the value matrix to obtain the initial state. AUBER-Reverse processes BERT starting from the final layer (e.g. 12th layer for BERT-base). Bold font indicates the best performance among pruning methods.
创建时间:
2021-06-28



