论文标题
用沙普利值解释偏好
Explaining Preferences with Shapley Values
论文作者
论文摘要
尽管偏好建模已成为机器学习的支柱之一,但偏好解释的问题仍然具有挑战性且无人驾驶。在本文中,我们建议\ textsc {pref-shap},这是一个基于沙普利价值的模型说明框架,用于成对比较数据。我们为偏好模型提供适当的值函数,并进一步扩展框架以建模并解释\ emph {context tempent}信息,例如网球游戏中的表面类型。为了演示\ textsc {pref-shap}的实用性,我们将方法应用于各种综合和现实世界数据集,并证明可以在基线上获得更丰富,更有见识的解释。
While preference modelling is becoming one of the pillars of machine learning, the problem of preference explanation remains challenging and underexplored. In this paper, we propose \textsc{Pref-SHAP}, a Shapley value-based model explanation framework for pairwise comparison data. We derive the appropriate value functions for preference models and further extend the framework to model and explain \emph{context specific} information, such as the surface type in a tennis game. To demonstrate the utility of \textsc{Pref-SHAP}, we apply our method to a variety of synthetic and real-world datasets and show that richer and more insightful explanations can be obtained over the baseline.