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.

翻译：深度神经网络已在众多应用领域取得了卓越成果。随着对高效稀疏深度学习模型需求的不断增长，模型压缩（尤其是剪枝）的重要性日益凸显。然而，传统剪枝方法可能无意中加剧算法偏见，导致关键应用中出现不平等的预测结果，从而引发对剪枝实践与社会公正之间矛盾的担忧。为应对这一挑战，我们提出了公平模型剪枝的新概念，即开发符合公平性准则的稀疏模型。具体而言，我们提出了一个在公平性约束下联合优化剪枝掩码与权重更新过程的框架。该框架旨在通过统一流程压缩模型，使其在保持性能的同时确保公平性。为此，我们将公平剪枝问题形式化为一种新颖的约束双层优化任务，并推导出高效且有效的求解策略。我们在多种数据集和场景下设计实验以验证所提方法。实证分析将我们的框架与多种主流剪枝策略进行对比，突显了本方法在保持模型公平性、性能与效率方面的优越性。