Viet-Anh on Software Logo

What is: Movement Pruning?

SourceMovement Pruning: Adaptive Sparsity by Fine-Tuning
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Movement Pruning is a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. Magnitude pruning can be seen as utilizing zeroth-order information (absolute value) of the running model. In contrast, movement pruning methods are where importance is derived from first-order information. Intuitively, instead of selecting weights that are far from zero, we retain connections that are moving away from zero during the training process.