On marginal feature attributions of tree-based models

• URL: http://arxiv.org/abs/2302.08434v4
• Date: Sun, 5 May 2024 22:39:16 GMT
• Title: On marginal feature attributions of tree-based models
• Authors: Khashayar Filom, Alexey Miroshnikov, Konstandinos Kotsiopoulos, Arjun Ravi Kannan,
• Abstract summary: Local feature attributions based on marginal expectations, e.g. marginal Shapley, Owen or Banzhaf values, may be employed. We present two (statistically similar) decision trees that compute the exact same function for which the "path-dependent" TreeSHAP yields different rankings of features. We exploit the symmetry to derive an explicit formula, with improved complexity and only in terms of the internal model parameters, for marginal Shapley (and Banzhaf and Owen) values of CatBoost models.
• Score: 0.11184789007828977
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to their power and ease of use, tree-based machine learning models, such as random forests and gradient-boosted tree ensembles, have become very popular. To interpret them, local feature attributions based on marginal expectations, e.g. marginal (interventional) Shapley, Owen or Banzhaf values, may be employed. Such methods are true to the model and implementation invariant, i.e. dependent only on the input-output function of the model. We contrast this with the popular TreeSHAP algorithm by presenting two (statistically similar) decision trees that compute the exact same function for which the "path-dependent" TreeSHAP yields different rankings of features, whereas the marginal Shapley values coincide. Furthermore, we discuss how the internal structure of tree-based models may be leveraged to help with computing their marginal feature attributions according to a linear game value. One important observation is that these are simple (piecewise-constant) functions with respect to a certain grid partition of the input space determined by the trained model. Another crucial observation, showcased by experiments with XGBoost, LightGBM and CatBoost libraries, is that only a portion of all features appears in a tree from the ensemble. Thus, the complexity of computing marginal Shapley (or Owen or Banzhaf) feature attributions may be reduced. This remains valid for a broader class of game values which we shall axiomatically characterize. A prime example is the case of CatBoost models where the trees are oblivious (symmetric) and the number of features in each of them is no larger than the depth. We exploit the symmetry to derive an explicit formula, with improved complexity and only in terms of the internal model parameters, for marginal Shapley (and Banzhaf and Owen) values of CatBoost models. This results in a fast, accurate algorithm for estimating these feature attributions.

Related papers

• Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles [6.664930499708017]
  The Shapley value (SV) is a concept in explainable artificial intelligence (XAI) research for quantifying additive feature attributions of predictions. We present TreeSHAP-IQ, an efficient method to compute any-order additive Shapley interactions for predictions tree-based models.
  arXiv  Detail & Related papers  (2024-01-22T16:08:41Z)
• 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)
• Interpretability at Scale: Identifying Causal Mechanisms in Alpaca [62.65877150123775]
  We use Boundless DAS to efficiently search for interpretable causal structure in large language models while they follow instructions. Our findings mark a first step toward faithfully understanding the inner-workings of our ever-growing and most widely deployed language models.
  arXiv  Detail & Related papers  (2023-05-15T17:15:40Z)
• Mixtures of All Trees [28.972995038976745]
  We propose a novel class of generative models called mixtures of all trees: that is, a mixture over all possible ($nn-2$) tree-shaped graphical models over $n$ variables. We show that it is possible to parameterize this Mixture of All Trees (MoAT) model compactly in a way that allows for tractable likelihood and optimization via gradient descent.
  arXiv  Detail & Related papers  (2023-02-27T23:37:03Z)
• Unboxing Tree Ensembles for interpretability: a hierarchical visualization tool and a multivariate optimal re-built tree [0.34530027457862006]
  We develop an interpretable representation of a tree-ensemble model that can provide valuable insights into its behavior. The proposed model is effective in yielding a shallow interpretable tree approxing the tree-ensemble decision function.
  arXiv  Detail & Related papers  (2023-02-15T10:43:31Z)
• Adaptive LASSO estimation for functional hidden dynamic geostatistical model [69.10717733870575]
  We propose a novel model selection algorithm based on a penalized maximum likelihood estimator (PMLE) for functional hiddenstatistical models (f-HD) The algorithm is based on iterative optimisation and uses an adaptive least absolute shrinkage and selector operator (GMSOLAS) penalty function, wherein the weights are obtained by the unpenalised f-HD maximum-likelihood estimators.
  arXiv  Detail & Related papers  (2022-08-10T19:17:45Z)
• TreeFlow: Going beyond Tree-based Gaussian Probabilistic Regression [0.0]
  We introduce TreeFlow, the tree-based approach that combines the benefits of using tree ensembles with the capabilities of modeling flexible probability distributions. We evaluate the proposed method on challenging regression benchmarks with varying volume, feature characteristics, and target dimensionality.
  arXiv  Detail & Related papers  (2022-06-08T20:06:23Z)
• Active-LATHE: An Active Learning Algorithm for Boosting the Error Exponent for Learning Homogeneous Ising Trees [75.93186954061943]
  We design and analyze an algorithm that boosts the error exponent by at least 40% when $rho$ is at least $0.8$. Our analysis hinges on judiciously exploiting the minute but detectable statistical variation of the samples to allocate more data to parts of the graph.
  arXiv  Detail & Related papers  (2021-10-27T10:45:21Z)
• A cautionary tale on fitting decision trees to data from additive models: generalization lower bounds [9.546094657606178]
  We study the generalization performance of decision trees with respect to different generative regression models. This allows us to elicit their inductive bias, that is, the assumptions the algorithms make (or do not make) to generalize to new data. We prove a sharp squared error generalization lower bound for a large class of decision tree algorithms fitted to sparse additive models.
  arXiv  Detail & Related papers  (2021-10-18T21:22:40Z)
• On the Discrepancy between Density Estimation and Sequence Generation [92.70116082182076]
  log-likelihood is highly correlated with BLEU when we consider models within the same family. We observe no correlation between rankings of models across different families.
  arXiv  Detail & Related papers  (2020-02-17T20:13:35Z)
• Particle-Gibbs Sampling For Bayesian Feature Allocation Models [77.57285768500225]
  Most widely used MCMC strategies rely on an element wise Gibbs update of the feature allocation matrix. We have developed a Gibbs sampler that can update an entire row of the feature allocation matrix in a single move. This sampler is impractical for models with a large number of features as the computational complexity scales exponentially in the number of features. We develop a Particle Gibbs sampler that targets the same distribution as the row wise Gibbs updates, but has computational complexity that only grows linearly in the number of features.
  arXiv  Detail & Related papers  (2020-01-25T22:11:51Z)

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.