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 GRAdient Pruning mEthod (FairGRAPE), that minimizes the disproportionate impacts of pruning on different sub-groups. Our method calculates the per-group importance of each model weight and selects a subset of weights that maintain the relative between-group total importance in pruning. The proposed method then prunes network edges with small importance values and repeats the procedure by updating importance values. We demonstrate the effectiveness of our method on four different datasets, FairFace, UTKFace, CelebA, and ImageNet, for the tasks of face attribute classification where our method reduces the disparity in performance degradation by up to 90% compared to the state-of-the-art pruning algorithms. Our method is substantially more effective in a setting with a high pruning rate (99%). The code and dataset used in the experiments are available at https://github.com/Bernardo1998/FairGRAPE
Code (1)
Tasks
AttributeFairnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
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 …
FairnessNetwork PruningCA-AFP: Cluster-Aware Adaptive Federated Pruning
Federated Learning (FL) faces major challenges in real-world deployments due to statistical heterogeneity across clients and system heterogeneity arising from resource-constrained devices. While clustering-based approach…
Human Activity RecognitionFederated LearningLess Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions
Model compression through post-training pruning offers a way to reduce model size and computational requirements without significantly impacting model performance. However, the effect of pruning on the fairness of LLM-ge…
Model CompressionFairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication
Recent dataset deduplication techniques have demonstrated that content-aware dataset pruning can dramatically reduce the cost of training Vision-Language Pretrained (VLP) models without significant performance losses com…
FairnessPrune 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+1