Adaptive Deep Reuse: Accelerating CNN Training on the Fly
Adaptive Deep Reuse: Accelerating CNN Training on the Fly
复制标题
DOI:
10.1109/icde.2019.00138
复制
发表时间:
2019-04
期刊:
影响因子:
--
通讯作者:
Lin Ning;Hui Guan;Xipeng Shen
中科院分区:
文献类型:
--
作者:
Lin Ning;Hui Guan;Xipeng Shen
This work proposes adaptive deep reuse, a method for accelerating CNN training by identifying and avoiding the unnecessary computations contained in each specific training on the fly. It makes two-fold major contributions. (1) It empirically proves the existence of a lot of similarities among neuron vectors in both forward and backward propagation of CNN. (2) It introduces the first adaptive strategy for translating the similarities into computation reuse in CNN training. The strategy adaptively adjusts the strength of reuse based on the different tolerance of precision relaxation in different CNN training stages. Experiments show that adaptive deep reuse saves 69% CNN training time with no accuracy loss.