Related papers: Explaining predictive models with mixed features using Shapley values and conditional inference trees

Explaining predictive models with mixed features using Shapley values and conditional inference trees

URL: http://arxiv.org/abs/2007.01027v1
Date: Thu, 2 Jul 2020 11:25:45 GMT
Title: Explaining predictive models with mixed features using Shapley values and conditional inference trees
Authors: Annabelle Redelmeier, Martin Jullum, and Kjersti Aas
Abstract summary: Shapley values stand out as a sound method to explain predictions from any type of machine learning model. We propose a method to explain mixed dependent features by modeling the dependence structure of the features using conditional inference trees.
Score: 1.8065361710947976
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: It is becoming increasingly important to explain complex, black-box machine learning models. Although there is an expanding literature on this topic, Shapley values stand out as a sound method to explain predictions from any type of machine learning model. The original development of Shapley values for prediction explanation relied on the assumption that the features being described were independent. This methodology was then extended to explain dependent features with an underlying continuous distribution. In this paper, we propose a method to explain mixed (i.e. continuous, discrete, ordinal, and categorical) dependent features by modeling the dependence structure of the features using conditional inference trees. We demonstrate our proposed method against the current industry standards in various simulation studies and find that our method often outperforms the other approaches. Finally, we apply our method to a real financial data set used in the 2018 FICO Explainable Machine Learning Challenge and show how our explanations compare to the FICO challenge Recognition Award winning team.

Related papers

Explaining Predictive Uncertainty with Information Theoretic Shapley Values [6.49838460559032]
We adapt the popular Shapley value framework to explain various types of predictive uncertainty. We implement efficient algorithms that perform well in a range of experiments on real and simulated data.
arXiv Detail & Related papers (2023-06-09T07:43:46Z)
Learning with Explanation Constraints [91.23736536228485]
We provide a learning theoretic framework to analyze how explanations can improve the learning of our models. We demonstrate the benefits of our approach over a large array of synthetic and real-world experiments.
arXiv Detail & Related papers (2023-03-25T15:06:47Z)
VCNet: A self-explaining model for realistic counterfactual generation [52.77024349608834]
Counterfactual explanation is a class of methods to make local explanations of machine learning decisions. We present VCNet-Variational Counter Net, a model architecture that combines a predictor and a counterfactual generator. We show that VCNet is able to both generate predictions, and to generate counterfactual explanations without having to solve another minimisation problem.
arXiv Detail & Related papers (2022-12-21T08:45:32Z)
MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
arXiv Detail & Related papers (2022-05-31T04:57:06Z)
Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models [77.34726150561087]
We define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. This paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications.
arXiv Detail & Related papers (2022-03-30T05:59:50Z)
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
arXiv Detail & Related papers (2021-03-18T12:57:34Z)
Unified Shapley Framework to Explain Prediction Drift [0.0]
We propose GroupShapley and GroupIG as axiomatically justified methods to tackle this problem. In doing so, we re-frame all current feature/data importance measures based on the Shapley value as essentially problems of distributional comparisons. We axiomatize certain desirable properties of distributional difference, and study the implications of choosing them.
arXiv Detail & Related papers (2021-02-15T21:58:19Z)
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)
Generative Temporal Difference Learning for Infinite-Horizon Prediction [101.59882753763888]
We introduce the $gamma$-model, a predictive model of environment dynamics with an infinite probabilistic horizon. We discuss how its training reflects an inescapable tradeoff between training-time and testing-time compounding errors.
arXiv Detail & Related papers (2020-10-27T17:54:12Z)
Accurate and Intuitive Contextual Explanations using Linear Model Trees [0.0]
Local post hoc model explanations have gained massive adoption. Current state of the art methods use rudimentary methods to generate synthetic data around the point to be explained. We use a Generative Adversarial Network for synthetic data generation and train a piecewise linear model in the form of Linear Model Trees.
arXiv Detail & Related papers (2020-09-11T10:13:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.