Timezone: »

Pruning has a disparate impact on model accuracy
Cuong Tran · Ferdinando Fioretto · Jung-Eun Kim · Rakshit Naidu

Tue Dec 06 05:00 PM -- 07:00 PM (PST) @

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, solution that mitigates the disparate impacts caused by pruning.

Author Information

Cuong Tran (Syracuse University)
Ferdinando Fioretto (Syracuse University)
Jung-Eun Kim (Computer Science, North Carolina State University)
Rakshit Naidu (School of Computer Science, Carnegie Mellon University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors