Disjunctive Threshold Networks for Tabular Data Classification
Disjunctive Threshold Networks for Tabular Data Classification
复制标题
DOI：
10.1109/ojcs.2023.3282948
复制
发表时间：
2023
影响因子：
5.9
通讯作者：
Weijia Wang;Litao Qiao;Bill Lin
中科院分区：
文献类型：
--
作者：
Weijia Wang;Litao Qiao;Bill Lin
虽然神经网络在解决自然语言处理等分类任务方面取得了越来越大的成就，但其缺乏可解释性成为神经网络在某些高风险的以人为本的应用中部署的巨大挑战。为了解决这个问题，我们提出了一种新的方法来生成可解释的预测，通过推断一个简单的三层神经网络与阈值激活，使它可以受益于有效的神经网络训练算法，并在同一时间，产生人类可理解的解释的结果。特别是，在所提出的模型中的隐藏层神经元训练浮点权重和二进制输出激活。输出神经元也可训练为实现析取操作的阈值逻辑函数，形成第一级阈值逻辑函数的逻辑或。该神经网络可以使用最先进的训练方法进行训练，以实现高预测精度。所提出的架构的一个重要特征是，只需要一个简单的贪婪算法来提供一个解释与预测，是人类可以理解的。与其他可解释的决策模型相比，我们提出的方法在广泛的表格数据分类数据集上实现了更准确的预测。
While neural networks have been achieving increasingly significant excitement in solving classification tasks such as natural language processing, their lack of interpretability becomes a great challenge for neural networks to be deployed in certain high-stakes human-centered applications. To address this issue, we propose a new approach for generating interpretable predictions by inferring a simple three-layer neural network with threshold activations, so that it can benefit from effective neural network training algorithms and at the same time, produce human-understandable explanations for the results. In particular, the hidden layer neurons in the proposed model are trained with floating point weights and binary output activations. The output neuron is also trainable as a threshold logic function that implements a disjunctive operation, forming the logical-OR of the first-level threshold logic functions. This neural network can be trained using state-of-the-art training methods to achieve high prediction accuracy. An important feature of the proposed architecture is that only a simple greedy algorithm is required to provide an explanation with the prediction that is human-understandable. In comparison with other explainable decision models, our proposed approach achieves more accurate predictions on a broad set of tabular data classification datasets.