Towards Fairness-aware Adversarial Network Pruning
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 raised a new perspective towards fairness-aware network pruning. Straightforward pruning plus debias methods and recent designs for monitoring disparities of demographic attributes during pruning have endeavored to enhance fairness in pruning. However, neither simple assembling of two tasks nor specifically designed pruning strategies could achieve the optimal trade-off among pruning ratio, accuracy, and fairness. This paper proposes an end-to-end learnable framework for fairness-aware network pruning, which optimizes both pruning and debias tasks jointly by adversarial training against those final evaluation metrics like accuracy for pruning, and disparate impact (DI) and equalized odds (DEO) for fairness. In other words, our fairness-aware adversarial pruning method would learn to prune without any handcraft rules. Therefore, our approach could flexibly adapt to variate network structures. Exhaustive experimentation demonstrates the generalization capacity of our approach, as well as superior performance on pruning and debias simultaneously. To highlight, the proposed method could preserve the SOTA pruning performance while significantly improving fairness by around 50% as compared to traditional pruning methods.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessNetwork PruningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification
Existing pruning techniques preserve deep neural networks' overall ability to make correct predictions but may also amplify hidden biases during the compression process. We propose a novel pruning method, Fairness-aware …
AttributeFairnessPrune Responsibly
Irrespective of the specific definition of fairness in a machine learning application, pruning the underlying model affects it. We investigate and document the emergence and exacerbation of undesirable per-class performa…
Decision MakingFairnessimage-classificationImage Classification+1Adversarial Attacks on Fairness of Graph Neural Networks
Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e.g., female) in graph-based applications. Although these methods greatly …
FairnessAttention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing
This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitive social contexts where fairness concern…
FairnessProgram RepairFairGAN: Fairness-aware Generative Adversarial Networks
Fairness-aware learning is increasingly important in data mining. Discrimination prevention aims to prevent discrimination in the training data before it is used to conduct predictive analysis. In this paper, we focus on…
FairnessGeneral Classification