Learning an explainable classifier often results in low accuracy model or ends up with a huge rule set, while learning a deep model is usually more capable of handling noisy data at scale, but with the cost of hard to explain the result and weak at generalization. To mitigate this gap, we propose an end-to-end deep explainable learning approach that combines the advantage of deep model in noise handling and expert rule-based interpretability. Specifically, we propose to learn a deep data assessing model which models the data as a graph to represent the correlations among different observations, whose output will be used to extract key data features. The key features are then fed into a rule network constructed following predefined noisy expert rules with trainable parameters. As these models are correlated, we propose an end-to-end training framework, utilizing the rule classification loss to optimize the rule learning model and data assessing model at the same time. As the rule-based computation is none-differentiable, we propose a gradient linking search module to carry the gradient information from the rule learning model to the data assessing model. The proposed method is tested in an industry production system, showing comparable prediction accuracy, much higher generalization stability and better interpretability when compared with a decent deep ensemble baseline, and shows much better fitting power than pure rule-based approach.
翻译:学习可解释的分类方法往往导致低精度模型,或最终形成一个巨大的规则集,而深深层次模型通常更能够处理规模的噪音数据,但代价是难以解释结果和一般化薄弱。为了缩小这一差距,我们提议一个端到端深层次的可解释学习方法,结合在噪音处理和专家基于规则的可解释性方面的深层模型的优势。具体地说,我们提议学习一个深层次的数据评估模型,将数据作为图表来模型,以代表不同观测的相互关系,其输出将被用于提取关键数据特征。然后,将关键特征输入一个按照预先定义的噪音专家规则以及可培训参数而构建的规则网络。由于这些模型是相互关联的,我们提议了一个端到端培训框架,利用规则分类损失来优化规则学习模式和在同一时间评估模型。由于基于规则的计算是无差别的,我们提议将一个梯度搜索模块,将数据从规则学习模式中的梯度信息与数据评估模型联系起来,而数据将被用于提取关键数据特征。拟议的方法将在一个行业生产系统中测试,显示可比的预测准确性、高得多的精度、精度比精度、更精度基线显示比更精度、更精度、更精度更精度更精度更精度、更精度更精确的基线性、更精度、更精确性、更精确性、更精确性、比于解释性、比于更精确性、比于更精确性、更精确性、更精确性、比更精确性、更精确性、更精确性、更精确性、更精确性、比更精确性、比更精确性、比更精确性、更精确性、更精确性、更精确性、比更精确性、比更精确性、比更精确性、比于比于解释性、更精确性、比更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、比更精确性、比比比比比比比比比于比比比比比比更精确性、更精确性、更精确性、更精确性、更精确性、更精确性、更精确