We provide a new approach to training neural models to exhibit transparency
in a well-defined, functional manner. Our approach naturally operates over
structured data and tailors the predictor, functionally, towards a chosen
family of (local) witnesses. The estimation problem is setup as a co-operative
game between an unrestricted predictor such as a neural network, and a set of
witnesses chosen from the desired transparent family. The goal of the witnesses
is to highlight, locally, how well the predictor conforms to the chosen family
of functions, while the predictor is trained to minimize the highlighted
discrepancy. We emphasize that the predictor remains globally powerful as it is
only encouraged to agree locally with locally adapted witnesses. We analyze the
effect of the proposed approach, provide example formulations in the context of
deep graph and sequence models, and empirically illustrate the idea in chemical
property prediction, temporal modeling, and molecule representation learning.

提出了一种新的方法来培训神经模型，使其以一种明确定义、功能性的方式呈现透明度，其中包括结构化数据和目标透明度家族中选择的本地证人，分析了该方法的效果，并在深度图和序列模型、化学性质预测、时间建模和分子表示学习等方面提供了实例阐述。