Pruning has a disparate impact on model accuracy. (arXiv:2205.13574v2 [cs.LG] UPDATED)

Network pruning is a widely-used compression technique that is able to
significantly scale down overparameterized models with minimal loss of
accuracy. This paper shows that pruning may create or exacerbate disparate
impacts. The paper sheds light on the factors to cause such disparities,
suggesting differences in gradient norms and distance to decision boundary
across groups to be responsible for this critical issue. It analyzes these
factors in detail, providing both theoretical and empirical support, and
proposes a simple, yet effective, …

accuracy arxiv impact lg model accuracy pruning