Efficient computation and analysis of distributional Shapley values

Abstract

Distributional data Shapley value (DShapley) has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning. DShapley develops the foundational game theory concept of Shapley values into a statistical framework and can be applied to identify data points that are useful (or harmful) to a learning algorithm. Estimating DShapley is computationally expensive, however, and this can be a major challenge to using it in practice. Moreover, there has been little mathematical analyses of how this value depends on data characteristics. In this paper, we derive the first analytic expressions for DShapley for the canonical problems of linear regression, binary classification, and non-parametric density estimation. These analytic forms provide new algorithms to estimate DShapley that are several orders of magnitude faster than previous state-of-the-art methods. Furthermore, our formulas are directly interpretable and provide quantitative insights into how the value varies for different types of data. We demonstrate the practical efficacy of our approach on multiple real and synthetic datasets.

arXiv comment24 pages, accepted for AISTATS 2021

References in corpus (15)

• Least Angle Regression
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Rejoinder to "Least angle regression" by Efron et al
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Data Shapley: Equitable Valuation of Data for Machine Learning
• Neuron Shapley: Discovering the Responsible Neurons
• A Distributional Framework for Data Valuation
• Data Market Platforms: Trading Data Assets to Solve Data Problems

Cited by in corpus (4)

• Improving Fairness for Data Valuation in Horizontal Federated Learning
• The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research
• DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
• Model-Agnostic Explanations using Minimal Forcing Subsets