Neural networks (NNs) have various applications in AI, but explaining their decisions remains challenging. Existing approaches often focus on explaining how changing individual inputs affects NNs' outputs. However, an explanation that is consistent with the input-output behaviour of an NN is not necessarily faithful to the actual mechanics thereof. In this paper, we exploit relationships between multi-layer perceptrons (MLPs) and quantitative argumentation frameworks (QAFs) to create argumentative explanations for the mechanics of MLPs. Our SpArX method first sparsifies the MLP while maintaining as much of the original structure as possible. It then translates the sparse MLP into an equivalent QAF to shed light on the underlying decision process of the MLP, producing global and/or local explanations. We demonstrate experimentally that SpArX can give more faithful explanations than existing approaches, while simultaneously providing deeper insights into the actual reasoning process of MLPs.

翻译：神经网络在人工智能领域有着广泛应用，但其决策过程的可解释性仍具挑战性。现有方法通常侧重于解释改变单个输入如何影响神经网络的输出。然而，与神经网络输入-输出行为一致的解释未必忠实于其实际运行机制。本文利用多层感知机（MLPs）与定量论证框架（QAFs）之间的关联，为MLPs的运行机制构建论证性解释。我们提出的SpArX方法首先在尽可能保持原始结构的前提下对MLP进行稀疏化，随后将稀疏化后的MLP转换为等价的QAF，以揭示MLP的底层决策过程，从而生成全局和/或局部解释。实验证明，SpArX能比现有方法提供更忠实的解释，同时更深入地揭示MLP的实际推理过程。