Bi-directional Masks for Efficient N: M Sparse Training.

Yuxin Zhang Yiting Luo Mingbao Lin Yunshan Zhong Jingjing Xie Fei Chao Rongrong Ji

Published in: ICML (2023)

Keyphrases

bi directional
data sets
training set
training examples
avoid overfitting
decision trees
training data
supervised learning
text classification
computationally efficient
neural network model