The Shapley value : essays in honor of Lloyd S. Shapley

By Alvin E. Roth, Lloyd S. Shapley. 1991

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Explainable machine-learning predictions for the prevention of hypoxaemia during surgery (2018, unknown): “…to use a model agnostic representation of feature importance, where the impact of each feature on the model is represented using Shapley values 18,36 , which have been shown to be the only way to assign feature importance while maintaining two important properties, local accuracy and consistency…”
Influence-Directed Explanations for Deep Convolutional Networks (2018, methodology): “This approach is inspired, in part, by axiomatic justification for power indices in cooperative game theory [13], [14]–an approach that has been previously employed for explaining predictions of machine learning models [15], [3].”
Inequality decomposition values: the trade-off between marginality and efficiency (2013, unknown): “In view of both its intuitive appeal and mathematical tractability, the Shapley value has been the focus of much research and applications (see for example the surveys of [1, 5, 12]).”
Towards better understanding of gradient-based attribution methods for Deep Neural Networks (2017, background): “Mathematically, In related literature, this property has been variously called Completeness (Sundararajan et al., 2017), Summation to Delta (Shrikumar et al., 2017) or Efﬁciency in the context of cooperative game theory (Roth, 1988), and often recognized as desirable for attribution methods.”
Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital (2021, background): “The Shapley value is a fair profit allocation among many stakeholders depending on their contribution [9] and was derived from the name of the economist who introduced it.”