Feature Importance: A Closer Look at Shapley Values and LOCO
- URL: http://arxiv.org/abs/2303.05981v1
- Date: Fri, 10 Mar 2023 15:32:11 GMT
- Title: Feature Importance: A Closer Look at Shapley Values and LOCO
- Authors: Isabella Verdinelli and Larry Wasserman
- Abstract summary: Two popular methods for defining variable importance are LOCO and Shapley Values.
We take a look at the properties of these methods and their advantages and disadvantages.
Contrary to some claims, Shapley values do not eliminate feature correlation.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: There is much interest lately in explainability in statistics and machine
learning. One aspect of explainability is to quantify the importance of various
features (or covariates). Two popular methods for defining variable importance
are LOCO (Leave Out COvariates) and Shapley Values. We take a look at the
properties of these methods and their advantages and disadvantages. We are
particularly interested in the effect of correlation between features which can
obscure interpretability. Contrary to some claims, Shapley values do not
eliminate feature correlation. We critique the game theoretic axioms for
Shapley values and suggest some new axioms. We propose new, more statistically
oriented axioms for feature importance and some measures that satisfy these
axioms. However, correcting for correlation is a Faustian bargain: removing the
effect of correlation creates other forms of bias. Ultimately, we recommend a
slightly modified version of LOCO. We briefly consider how to modify Shapley
values to better address feature correlation.
Related papers
- Efficient Shapley Values Estimation by Amortization for Text
Classification [66.7725354593271]
We develop an amortized model that directly predicts each input feature's Shapley Value without additional model evaluations.
Experimental results on two text classification datasets demonstrate that our amortized model estimates Shapley Values accurately with up to 60 times speedup.
arXiv Detail & Related papers (2023-05-31T16:19:13Z) - WeightedSHAP: analyzing and improving Shapley based feature attributions [17.340091573913316]
Shapley value is a popular approach for measuring the influence of individual features.
We propose WeightedSHAP, which generalizes the Shapley value and learns which marginal contributions to focus directly from data.
On several real-world datasets, we demonstrate that the influential features identified by WeightedSHAP are better able to recapitulate the model's predictions.
arXiv Detail & Related papers (2022-09-27T14:34:07Z) - On the Strong Correlation Between Model Invariance and Generalization [54.812786542023325]
Generalization captures a model's ability to classify unseen data.
Invariance measures consistency of model predictions on transformations of the data.
From a dataset-centric view, we find a certain model's accuracy and invariance linearly correlated on different test sets.
arXiv Detail & Related papers (2022-07-14T17:08:25Z) - Is Shapley Explanation for a model unique? [0.0]
We explore the relationship between the distribution of a feature and its Shapley value.
Our assessment is that Shapley value for particular feature not only depends on its expected mean but on other moments as well such as variance.
It varies with model outcome (Probability/Log-odds/binary decision such as accept vs reject) and hence model application.
arXiv Detail & Related papers (2021-11-23T15:31:46Z) - On Quantitative Evaluations of Counterfactuals [88.42660013773647]
This paper consolidates work on evaluating visual counterfactual examples through an analysis and experiments.
We find that while most metrics behave as intended for sufficiently simple datasets, some fail to tell the difference between good and bad counterfactuals when the complexity increases.
We propose two new metrics, the Label Variation Score and the Oracle score, which are both less vulnerable to such tiny changes.
arXiv Detail & Related papers (2021-10-30T05:00:36Z) - Joint Shapley values: a measure of joint feature importance [6.169364905804678]
We introduce joint Shapley values, which directly extend the Shapley axioms.
Joint Shapley values measure a set of features' average effect on a model's prediction.
Results for games show that joint Shapley values present different insights from existing interaction indices.
arXiv Detail & Related papers (2021-07-23T17:22:37Z) - Search Methods for Sufficient, Socially-Aligned Feature Importance
Explanations with In-Distribution Counterfactuals [72.00815192668193]
Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time.
We study several under-explored dimensions of FI-based explanations, providing conceptual and empirical improvements for this form of explanation.
arXiv Detail & Related papers (2021-06-01T20:36:48Z) - Counterfactual Invariance to Spurious Correlations: Why and How to Pass
Stress Tests [87.60900567941428]
A spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter.
In machine learning, these have a know-it-when-you-see-it character.
We study stress testing using the tools of causal inference.
arXiv Detail & Related papers (2021-05-31T14:39:38Z) - Fundamental Limits and Tradeoffs in Invariant Representation Learning [99.2368462915979]
Many machine learning applications involve learning representations that achieve two competing goals.
Minimax game-theoretic formulation represents a fundamental tradeoff between accuracy and invariance.
We provide an information-theoretic analysis of this general and important problem under both classification and regression settings.
arXiv Detail & Related papers (2020-12-19T15:24:04Z) - Multicollinearity Correction and Combined Feature Effect in Shapley
Values [0.0]
Shapley values represent the importance of a feature for a particular row.
We present a unified framework to calculate Shapley values with correlated features.
arXiv Detail & Related papers (2020-11-03T12:28:42Z) - Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual
Predictions of Complex Models [6.423239719448169]
Shapley values are designed to attribute the difference between a model's prediction and an average baseline to the different features used as input to the model.
We show how these 'causal' Shapley values can be derived for general causal graphs without sacrificing any of their desirable properties.
arXiv Detail & Related papers (2020-11-03T11:11:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.