Fetching the paper…
Reading the bibliography…
The true population-level importance of a variable in a prediction task provides useful knowledge about the underlying data-generating mechanism and can help in deciding which measurements to collect in subsequent experiments.
A value for n-person games
LS Shapley · 1953
Earlier work this paper cites.
Extremal principle solutions of games in characteristic function form: core, Chebychev and Shapley value generalizations
A Charnes, B Golany, M Keane, and J Rousseau · 1988
Earlier work this paper cites.
Generalized Additive Models , volume 43
TJ Hastie and RJ Tibshirani · 1990
Earlier work this paper cites.
Interpreting neural network connection weights
DG Garson · 1991
Earlier work this paper cites.
Asymptotic Statistics , volume 3
AW van der Vaart · 2000
Earlier work this paper cites.
Random forests
L Breiman · 2001
Earlier work this paper cites.
Greedy function approximation: a gradient boosting machine
JH Friedman · 2001
Earlier work this paper cites.
Convex optimization
S Boyd and L Vandenberghe · 2004
Earlier work this paper cites.
Understanding global feature contributions through additive importance measures
I Covert, S Lundberg, and SI Lee · 2004
Earlier work this paper cites.
A unified approach for inference on algorithm-agnostic variable importance
BD Williamson, PB Gilbert, N Simon, and M Carone · 2004
Cited alongside, same era.
Boosting with early stopping: Convergence and consistency
T Zhang and B Yu · 2005
Cited alongside, same era.
A model for immunological correlates of protection
AJ Dunning · 2006
Cited alongside, same era.
Estimators of relative importance in linear regression based on variance decomposition
U Grömping · 2007
Cited alongside, same era.
Polynomial calculation of the shapley value based on sampling
J Castro, D Gómez, and J Tejada · 2009
Cited alongside, same era.
Interpreting multiple linear regression: A guidebook of variable importance
LL Nathans, FL Oswald, and K Nimon · 2012
Explaining prediction models and individual predictions with feature contributions
E Štrumbelj and I Kononenko · 2014
Later among the works it cites.
XGBoost: A Scalable Tree Boosting System
T Chen and C Guestrin · 2016
Later among the works it cites.
Why should I trust you?: Explaining the predictions of any classifier
MT Ribeiro, S Singh, and C Guestrin · 2016
Later among the works it cites.
A unified approach to interpreting model predictions
SM Lundberg and S-I Lee · 2017
Later among the works it cites.
On Shapley value for measuring importance of dependent units
AB Owen and C Prieur · 2017
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Predicting in-hospital mortality of icu patients: The physionet/computing in cardiology challenge 2012
I Silva, G Moody, DJ Scott, LA Celi, and RG Mark · 2012
Cited alongside, same era.
Adam: A method for stochastic optimization
D Kingma and J Ba · 2014
Cited alongside, same era.
Nonparametric variable importance assessment using machine learning techniques
BD Williamson, PB Gilbert, M Carone, and N Simon
Cited in the paper.
M Arjovsky, L Bottou, I Gulrajani, and D Lopez-Paz · 2019
Later among the works it cites.
Interpretable machine learning: definitions, methods, and applications
WJ Murdoch, C Singh, K Kumbier, R Abbasi-Asl, and B Yu · 2019
Later among the works it cites.
From local explanations to global understanding with explainable AI for trees
SM Lundberg, G Erion, H Chen, A DeGrave, et al · 2020
Closest in time.