Rule-based surrogate models are an effective and interpretable way to approximate a Deep Neural Network's (DNN) decision boundaries, allowing humans to easily understand deep learning models. Current state-of-the-art decompositional methods, which are those that consider the DNN's latent space to extract more exact rule sets, manage to derive rule sets at high accuracy. However, they a) do not guarantee that the surrogate model has learned from the same variables as the DNN (alignment), b) only allow to optimise for a single objective, such as accuracy, which can result in excessively large rule sets (complexity), and c) use decision tree algorithms as intermediate models, which can result in different explanations for the same DNN (stability). This paper introduces the CGX (Column Generation eXplainer) to address these limitations - a decompositional method using dual linear programming to extract rules from the hidden representations of the DNN. This approach allows to optimise for any number of objectives and empowers users to tweak the explanation model to their needs. We evaluate our results on a wide variety of tasks and show that CGX meets all three criteria, by having exact reproducibility of the explanation model that guarantees stability and reduces the rule set size by >80% (complexity) at equivalent or improved accuracy and fidelity across tasks (alignment).
翻译:摘要:基于规则的代理模型是一种有效且具有可解释性的近似深度神经网络决策边界的方式,使人类能够轻松理解深度学习模型。目前最先进的分解方法,这些方法考虑DNN的潜在空间以提取更精确的规则集,能够在高精度上导出规则集。然而,它们 a) 不能保证代理模型已从与DNN相同的变量中学习(对齐),b) 只允许优化单个目标,例如准确性,这可能导致过多的规则集(复杂度),c) 使用决策树算法作为中间模型,这可能导致相同DNN的不同解释(稳定性)。本文提出了CGX(列生成解释器)来解决这些限制问题---一种使用双线性规划从DNN的隐藏表示中提取规则的分解方法。该方法可优化任意数量的目标,并赋予用户根据需要调整解释模型的权利。我们在各种任务上评估了结果,并显示CGX满足所有三个标准,具有确切的解释模型的可重现性,保证稳定性并将规则集大小降低了 > 80%(复杂度),并在等效或提高的准确性和信度下跨任务改善对齐.