Timezone: »

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

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #933

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)
Ferdinando Fioretto

I am an assistant professor of Computer Science at UVA. I lead the Responsible AI for Science and Engineering (RAISE) group where we make advances in artificial intelligence with focus on two key themes: - AI for Science and Engineering: We develop the foundations to blend deep learning and constrained optimization for complex scientific and engineering problems. - Trustworthy & Responsible AI: We analyze the equity of AI systems in support of decision-making and learning tasks, focusing especially on privacy and fairness.

Jung-Eun Kim (Computer Science, North Carolina State University)
Rakshit Naidu (School of Computer Science, Carnegie Mellon University)

More from the Same Authors