Training Your Sparse Neural Network Better with Any Mask. (arXiv:2206.12755v2 [cs.CV] UPDATED)

Pruning large neural networks to create high-quality, independently trainable
sparse masks, which can maintain similar performance to their dense
counterparts, is very desirable due to the reduced space and time complexity.
As research effort is focused on increasingly sophisticated pruning methods
that leads to sparse subnetworks trainable from the scratch, we argue for an
orthogonal, under-explored theme: improving training techniques for pruned
sub-networks, i.e. sparse training. Apart from the popular belief that only the
quality of sparse masks matters for …

arxiv cv network neural network training