We show how solution concepts from cooperative game theory can be used to tackle the problem of pruning neural networks. The ever-growing size of deep neural networks (DNNs) increases their performance, but also their computational requirements. We introduce a method called Game Theory Assisted Pruning (GTAP), which reduces the neural network's size while preserving its predictive accuracy. GTAP is based on eliminating neurons in the network based on an estimation of their joint impact on the prediction quality through game theoretic solutions. Specifically, we use a power index akin to the Shapley value or Banzhaf index, tailored using a procedure similar to Dropout (commonly used to tackle overfitting problems in machine learning). Empirical evaluation of both feedforward networks and convolutional neural networks shows that this method outperforms existing approaches in the achieved tradeoff between the number of parameters and model accuracy.

翻译：我们展示了如何利用合作博弈论中的解概念来应对神经网络剪枝问题。深度神经网络规模的持续扩大虽提升了其性能，却也增加了计算需求。我们提出了一种名为"博弈论辅助剪枝"（GTAP）的方法，该方法能在减小神经网络规模的同时保持其预测精度。GTAP的核心在于：通过博弈论解估算神经元对预测质量的联合影响，并据此消除冗余神经元。具体而言，我们采用类似Shapley值或Banzhaf指数的势指标，并借助类似Dropout（常用于解决机器学习过拟合问题）的流程进行定制。对前馈网络和卷积神经网络的实证评估表明，该方法在参数数量与模型精度的权衡上优于现有方案。