Deep neural networks (DNNs) have found successful applications in many fields, but their black-box nature hinders interpretability. This is addressed by the neural additive model (NAM), in which the network is divided into additive sub-networks, thus making apparent the interaction between input features and predictions. In this paper, we approach the additive structure from a Bayesian perspective and develop a practical Laplace approximation. This enhances interpretability in three primary ways: a) It provides credible intervals for the recovered feature interactions by estimating function-space uncertainty of the sub-networks; b) it yields a tractable estimate of the marginal likelihood, which can be used to perform an implicit selection of features through an empirical Bayes procedure; and c) it can be used to rank feature pairs as candidates for second-order interactions in fine-tuned interaction models. We show empirically that our proposed Laplace-approximated NAM (LA-NAM) improves performance and interpretability on tabular regression and classification datasets and challenging real-world medical tasks.

翻译：深度神经网络（DNNs）已在众多领域成功应用，但其黑箱特性阻碍了可解释性。神经加性模型（NAM）通过将网络分解为多个加性子网络，使输入特征与预测之间的交互关系得以清晰呈现。本文从贝叶斯视角出发对加性结构进行建模，并开发了一种实用的拉普拉斯近似方法。该方法从三个主要方面增强可解释性：a）通过估计子网络函数空间的不确定性，为恢复的特征交互提供置信区间；b）得到边际似然的易处理估计，可基于经验贝叶斯流程实现特征的隐式选择；c）可对特征对进行排序，作为精细调优交互模型中二阶交互的候选对象。实验证明，所提出的拉普拉斯近似NAM（LA-NAM）在表格回归与分类数据集以及具有挑战性的真实医疗任务中，均能提升模型性能与可解释性。