Integrating Fairness and Model Pruning Through Bi-level Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913764663623680 |
|---|---|
| author | Dai, Yucong Li, Gen Luo, Feng Ma, Xiaolong Wu, Yongkai |
| author_facet | Dai, Yucong Li, Gen Luo, Feng Ma, Xiaolong Wu, Yongkai |
| contents | Deep neural networks have achieved exceptional results across a range of applications. As the demand for efficient and sparse deep learning models escalates, the significance of model compression, particularly pruning, is increasingly recognized. Traditional pruning methods, however, can unintentionally intensify algorithmic biases, leading to unequal prediction outcomes in critical applications and raising concerns about the dilemma of pruning practices and social justice. To tackle this challenge, we introduce a novel concept of fair model pruning, which involves developing a sparse model that adheres to fairness criteria. In particular, we propose a framework to jointly optimize the pruning mask and weight update processes with fairness constraints. This framework is engineered to compress models that maintain performance while ensuring fairness in a unified process. To this end, we formulate the fair pruning problem as a novel constrained bi-level optimization task and derive efficient and effective solving strategies. We design experiments across various datasets and scenarios to validate our proposed method. Our empirical analysis contrasts our framework with several mainstream pruning strategies, emphasizing our method's superiority in maintaining model fairness, performance, and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_10181 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Integrating Fairness and Model Pruning Through Bi-level Optimization Dai, Yucong Li, Gen Luo, Feng Ma, Xiaolong Wu, Yongkai Machine Learning Artificial Intelligence Computers and Society Deep neural networks have achieved exceptional results across a range of applications. As the demand for efficient and sparse deep learning models escalates, the significance of model compression, particularly pruning, is increasingly recognized. Traditional pruning methods, however, can unintentionally intensify algorithmic biases, leading to unequal prediction outcomes in critical applications and raising concerns about the dilemma of pruning practices and social justice. To tackle this challenge, we introduce a novel concept of fair model pruning, which involves developing a sparse model that adheres to fairness criteria. In particular, we propose a framework to jointly optimize the pruning mask and weight update processes with fairness constraints. This framework is engineered to compress models that maintain performance while ensuring fairness in a unified process. To this end, we formulate the fair pruning problem as a novel constrained bi-level optimization task and derive efficient and effective solving strategies. We design experiments across various datasets and scenarios to validate our proposed method. Our empirical analysis contrasts our framework with several mainstream pruning strategies, emphasizing our method's superiority in maintaining model fairness, performance, and efficiency. |
| title | Integrating Fairness and Model Pruning Through Bi-level Optimization |
| topic | Machine Learning Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2312.10181 |