On Model Extrapolation in Marginal Shapley Values

• URL: http://arxiv.org/abs/2412.13158v1
• Date: Tue, 17 Dec 2024 18:33:14 GMT
• Title: On Model Extrapolation in Marginal Shapley Values
• Authors: Ilya Rozenfeld,
• Abstract summary: One of the most popular methods for model explainability is based on Shapley values. marginal approach to calculating Shapley values leads to model extrapolation where it might not be well defined. We propose an approach which while using marginal averaging avoids model extrapolation and with addition of causal information replicates causal Shapley values.
• Score: 0.0
• License:
• Abstract: As the use of complex machine learning models continues to grow, so does the need for reliable explainability methods. One of the most popular methods for model explainability is based on Shapley values. There are two most commonly used approaches to calculating Shapley values which produce different results when features are correlated, conditional and marginal. In our previous work, it was demonstrated that the conditional approach is fundamentally flawed due to implicit assumptions of causality. However, it is a well-known fact that marginal approach to calculating Shapley values leads to model extrapolation where it might not be well defined. In this paper we explore the impacts of model extrapolation on Shapley values in the case of a simple linear spline model. Furthermore, we propose an approach which while using marginal averaging avoids model extrapolation and with addition of causal information replicates causal Shapley values. Finally, we demonstrate our method on the real data example.

Related papers

• Shapley Marginal Surplus for Strong Models [0.9831489366502301]
  We show that while Shapley values might be accurate explainers of model predictions, machine learning models themselves are often poor explainers of the true data-generating process (DGP) We introduce a novel variable importance algorithm, Shapley Marginal Surplus for Strong Models, that samples the space of possible models to come up with an inferential measure of feature importance.
  arXiv  Detail & Related papers  (2024-08-16T17:06:07Z)
• 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)
• Manifold Restricted Interventional Shapley Values [0.5156484100374059]
  We propose emphManifoldShap, which respects the model's domain of validity by restricting model evaluations to the data manifold. We show, theoretically and empirically, that ManifoldShap is robust to off-manifold perturbations of the model and leads to more accurate and intuitive explanations.
  arXiv  Detail & Related papers  (2023-01-10T15:47:49Z)
• Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
  Causal mechanisms can be described by structural causal models. One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
  arXiv  Detail & Related papers  (2021-09-06T14:52:58Z)
• Explaining predictive models using Shapley values and non-parametric vine copulas [2.6774008509840996]
  We propose two new approaches for modelling the dependence between the features. The performance of the proposed methods is evaluated on simulated data sets and a real data set. Experiments demonstrate that the vine copula approaches give more accurate approximations to the true Shapley values than its competitors.
  arXiv  Detail & Related papers  (2021-02-12T09:43:28Z)
• Distilling Interpretable Models into Human-Readable Code [71.11328360614479]
  Human-readability is an important and desirable standard for machine-learned model interpretability. We propose to train interpretable models using conventional methods, and then distill them into concise, human-readable code. We describe a piecewise-linear curve-fitting algorithm that produces high-quality results efficiently and reliably across a broad range of use cases.
  arXiv  Detail & Related papers  (2021-01-21T01:46:36Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)
• 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)
• Non-parametric Models for Non-negative Functions [48.7576911714538]
  We provide the first model for non-negative functions from the same good linear models. We prove that it admits a representer theorem and provide an efficient dual formulation for convex problems.
  arXiv  Detail & Related papers  (2020-07-08T07:17:28Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)

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.