Joint Shapley values: a measure of joint feature importance
- URL: http://arxiv.org/abs/2107.11357v1
- Date: Fri, 23 Jul 2021 17:22:37 GMT
- Title: Joint Shapley values: a measure of joint feature importance
- Authors: Chris Harris, Richard Pymar, Colin Rowat
- Abstract summary: 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.
- Score: 6.169364905804678
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The Shapley value is one of the most widely used model-agnostic measures of
feature importance in explainable AI: it has clear axiomatic foundations, is
guaranteed to uniquely exist, and has a clear interpretation as a feature's
average effect on a model's prediction. We introduce joint Shapley values,
which directly extend the Shapley axioms. This preserves the classic Shapley
value's intuitions: joint Shapley values measure a set of features' average
effect on a model's prediction. We prove the uniqueness of joint Shapley
values, for any order of explanation. Results for games show that joint Shapley
values present different insights from existing interaction indices, which
assess the effect of a feature within a set of features. Deriving joint Shapley
values in ML attribution problems thus gives us the first measure of the joint
effect of sets of features on model predictions. In a dataset with binary
features, we present a presence-adjusted method for calculating global values
that retains the efficiency property.
Related papers
- Fast Shapley Value Estimation: A Unified Approach [71.92014859992263]
We propose a straightforward and efficient Shapley estimator, SimSHAP, by eliminating redundant techniques.
In our analysis of existing approaches, we observe that estimators can be unified as a linear transformation of randomly summed values from feature subsets.
Our experiments validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
arXiv Detail & Related papers (2023-11-02T06:09:24Z) - 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) - Variable Importance Matching for Causal Inference [73.25504313552516]
We describe a general framework called Model-to-Match that achieves these goals.
Model-to-Match uses variable importance measurements to construct a distance metric.
We operationalize the Model-to-Match framework with LASSO.
arXiv Detail & Related papers (2023-02-23T00:43:03Z) - 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) - Faith-Shap: The Faithful Shapley Interaction Index [43.968337274203414]
A key attraction of Shapley values is that they uniquely satisfy a very natural set of axiomatic properties.
We show that by requiring the faithful interaction indices to satisfy interaction-extensions of the standard individual Shapley axioms, we obtain a unique Faithful Shapley Interaction index.
arXiv Detail & Related papers (2022-03-02T04:44:52Z) - Exact Shapley Values for Local and Model-True Explanations of Decision
Tree Ensembles [0.0]
We consider the application of Shapley values for explaining decision tree ensembles.
We present a novel approach to Shapley value-based feature attribution that can be applied to random forests and boosted decision trees.
arXiv Detail & Related papers (2021-12-16T20:16:02Z) - Counterfactual Shapley Additive Explanations [6.916452769334367]
We propose a variant of SHAP, CoSHAP, that uses counterfactual generation techniques to produce a background dataset.
We motivate the need within the actionable recourse setting for careful consideration of background datasets when using Shapley values for feature attributions.
arXiv Detail & Related papers (2021-10-27T08:44:53Z) - 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) - Predictive and Causal Implications of using Shapley Value for Model
Interpretation [6.744385328015561]
We established the relationship between Shapley value and conditional independence, a key concept in both predictive and causal modeling.
Our results indicate that, eliminating a variable with high Shapley value from a model do not necessarily impair predictive performance.
More importantly, Shapley value of a variable do not reflect their causal relationship with the target of interest.
arXiv Detail & Related papers (2020-08-12T01:08:08Z) - Slice Sampling for General Completely Random Measures [74.24975039689893]
We present a novel Markov chain Monte Carlo algorithm for posterior inference that adaptively sets the truncation level using auxiliary slice variables.
The efficacy of the proposed algorithm is evaluated on several popular nonparametric models.
arXiv Detail & Related papers (2020-06-24T17:53:53Z) - Towards Efficient Data Valuation Based on the Shapley Value [65.4167993220998]
We study the problem of data valuation by utilizing the Shapley value.
The Shapley value defines a unique payoff scheme that satisfies many desiderata for the notion of data value.
We propose a repertoire of efficient algorithms for approximating the Shapley value.
arXiv Detail & Related papers (2019-02-27T00:22:43Z)
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.