This paper proposes an algorithm called Forward Composition Propagation (FCP) to explain the predictions of feed-forward neural networks operating on structured classification problems. In the proposed FCP algorithm, each neuron is described by a composition vector indicating the role of each problem feature in that neuron. Composition vectors are initialized using a given input instance and subsequently propagated through the whole network until reaching the output layer. The sign of each composition value indicates whether the corresponding feature excites or inhibits the neuron, while the absolute value quantifies its impact. The FCP algorithm is executed on a post-hoc basis, i.e., once the learning process is completed. Aiming to illustrate the FCP algorithm, this paper develops a case study concerning bias detection in a fairness problem in which the ground truth is known. The simulation results show that the composition values closely align with the expected behavior of protected features. The source code and supplementary material for this paper are available at https://github.com/igraugar/fcp.

中文翻译：

---

用于可解释神经推理的前向组合传播


本文提出了一种称为前向组合传播（FCP）的算法来解释前馈神经网络在结构化分类问题上的预测。在所提出的 FCP 算法中，每个神经元都由一个复合向量来描述，该向量指示每个问题特征在该神经元中的作用。组合向量使用给定的输入实例进行初始化，然后通过整个网络传播，直到到达输出层。每个成分值的符号表示相应的特征是兴奋还是抑制神经元，而绝对值则量化其影响。 FCP 算法是事后执行的，即学习过程完成后执行。为了说明 FCP 算法，本文开发了一个有关已知基本事实的公平问题中的偏差检测的案例研究。模拟结果表明，成分值与受保护特征的预期行为密切相关。本文的源代码和补充材料可在 https://github.com/igraugar/fcp 获取。