paper-with-me

홈 › Papers

Pruning has a disparate impact on model accuracy

2022-05-26 · Cuong Tran, Ferdinando Fioretto, Jung-eun Kim, Rakshit Naidu

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.

📄 PDF Abstract BibTeX arXiv:2205.13574

Code (0)

등록된 구현이 없습니다.

Tasks

Network Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Balancing Act: Constraining Disparate Impact in Sparse Models

2023-10-31 · Meraj Hashemizadeh, Juan Ramirez, Rohan Sukumaran, Golnoosh Farnadi 외

Model pruning is a popular approach to enable the deployment of large deep learning models on edge devices with restricted computational or storage capacities. Although sparse models achieve performance comparable to tha…

Selective Brain Damage: Measuring the Disparate Impact of Model Pruning

2019-09-25 · Sara Hooker, Yann Dauphin, Aaron Courville, Andrea Frome

Neural network pruning techniques have demonstrated it is possible to remove the majority of weights in a network with surprisingly little degradation to top-1 test set accuracy. However, this measure of performance conc…

Network Pruning

Towards Fairness-aware Adversarial Network Pruning

2023-01-01 · ICCV 2023 1 · Lei Zhang, Zhibo Wang, Xiaowei Dong, Yunhe Feng 외

Network pruning aims to compress models while minimizing loss in accuracy. With the increasing focus on bias in AI systems, the bias inheriting or even magnification nature of traditional network pruning methods has …

FairnessNetwork Pruning

What Do Compressed Deep Neural Networks Forget?

2019-11-13 · Sara Hooker, Aaron Courville, Gregory Clark, Yann Dauphin 외

Deep neural network pruning and quantization techniques have demonstrated it is possible to achieve high levels of compression with surprisingly little degradation to test set accuracy. However, this measure of performan…

FairnessInterpretability Techniques for Deep LearningModel CompressionNetwork Pruning+2

Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy

2020-03-08 · Depeng Xu, Wei Du, Xintao Wu

When we enforce differential privacy in machine learning, the utility-privacy trade-off is different w.r.t. each group. Gradient clipping and random noise addition disproportionately affect underrepresented and complex c…