Game-Theoretic Interpretability for Temporal Modeling
Game-Theoretic Interpretability for Temporal Modeling
复制标题
时间建模的博弈论可解释性
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
T. Jaakkola
中科院分区：
文献类型：
--
作者：
Guang;David Alvarez;T. Jaakkola
可解释性已经成为机器学习模型与性能的关键需求。到目前为止，方法主要关注的是强调特征相关性或选择的固定维度输入。相比之下，我们专注于时间建模和剪裁的预测，功能上，对一个可解释的家庭的问题。为此，我们提出了一个合作的预测和解释者之间的游戏，没有任何先验限制的功能类的预测。解释器的目标是突出显示，局部，以及预测符合所选择的可解释的时间模型的家庭。我们的合作博弈是建立在信息集的效率原因不对称。我们开发和说明的时间序列模型的背景下，与例子的框架。
Interpretability has arisen as a key desideratum of machine learning models alongside performance. Approaches so far have been primarily concerned with fixed dimensional inputs emphasizing feature relevance or selection. In contrast, we focus on temporal modeling and the problem of tailoring the predictor, functionally, towards an interpretable family. To this end, we propose a co-operative game between the predictor and an explainer without any a priori restrictions on the functional class of the predictor. The goal of the explainer is to highlight, locally, how well the predictor conforms to the chosen interpretable family of temporal models. Our co-operative game is setup asymmetrically in terms of information sets for efficiency reasons. We develop and illustrate the framework in the context of temporal sequence models with examples.