Deep neural networks have demonstrated remarkable performance in various tasks. With a growing need for sparse deep learning, model compression techniques, especially pruning, have gained significant attention. However, conventional pruning techniques can inadvertently exacerbate algorithmic bias, resulting in unequal predictions. To address this, we define a fair pruning task where a sparse model is derived subject to fairness requirements. 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 single execution. 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 spanning various datasets and settings 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：深度神经网络已在各类任务中展现出卓越性能。随着稀疏深度学习需求的增长，模型压缩技术特别是剪枝技术获得了广泛关注。然而，传统剪枝技术可能会在无意中加剧算法偏差，导致预测结果的不平等。为解决此问题，我们定义了一项公平剪枝任务，即在满足公平性要求的前提下导出稀疏模型。具体而言，我们提出了一种框架，在公平性约束下联合优化剪枝掩码和权重更新过程。该框架旨在通过单次执行实现压缩模型在保持性能的同时确保公平性。为此，我们将公平剪枝问题建模为新型约束双层优化任务，并推导出高效有效的求解策略。我们设计了涵盖多种数据集与场景的实验以验证所提方法。通过将我们框架与多种主流剪枝策略进行对比分析，实证结果凸显了本方法在维持模型公平性、性能和效率方面的优越性。