[Submitted on 15 Dec 2023 (v1), last revised 14 Nov 2026 (this version, v3)]
Abstract:Deep neural networks achieve high predictive performance but often require substantial computational and storage resources, which motivates model compression techniques such as neural network pruning. Conventional pruning methods, however, can introduce or amplify algorithmic bias and produce disparate outcomes across demographic groups. We study fair model pruning, which seeks sparse models that satisfy fairness criteria while maintaining predictive performance. We characterize fairness using both group accuracy disparity and differences in compression-induced accuracy degradation across demographic groups. We propose a framework that jointly optimizes pruning masks and model weights under fairness constraints, thereby integrating accuracy and fairness into the compression process. We formulate fair pruning as a constrained bi-level optimization problem and derive an efficient optimization procedure. Experiments across multiple datasets, predictive tasks, model architectures, and sparsity levels show that our framework improves the trade-off among fairness, accuracy, and training efficiency relative to the baseline pruning strategies. Compared with the strongest evaluated baselines, BiFP maintains competitive accuracy and fairness while requiring more than 94% fewer training iterations in the real-world experiments.
Submission history
From: Yongkai Wu [view email]
[v1] Fri, 15 Dec 2023 20:08:53 UTC (1,807 KB)
[v2] Sat, 29 Mar 2025 01:56:39 UTC (1,659 KB)
[v3] Sat, 14 Nov 2026 19:02:50 UTC (1,668 KB)
