A Baseline for Shapley Values in MLPs: from Missingness to Neutrality

• URL: http://arxiv.org/abs/2006.04896v3
• Date: Mon, 9 Aug 2021 20:20:01 GMT
• Title: A Baseline for Shapley Values in MLPs: from Missingness to Neutrality
• Authors: Cosimo Izzo and Aldo Lipani and Ramin Okhrati and Francesca Medda
• Abstract summary: Deep neural networks have gained momentum based on their accuracy, but their interpretability is often criticised. In this paper, we present a method for choosing a baseline according to a neutrality value. We empirically validate our choice of baseline in the context of binary classification tasks.
• Score: 3.5939555573102853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have gained momentum based on their accuracy, but their interpretability is often criticised. As a result, they are labelled as black boxes. In response, several methods have been proposed in the literature to explain their predictions. Among the explanatory methods, Shapley values is a feature attribution method favoured for its robust theoretical foundation. However, the analysis of feature attributions using Shapley values requires choosing a baseline that represents the concept of missingness. An arbitrary choice of baseline could negatively impact the explanatory power of the method and possibly lead to incorrect interpretations. In this paper, we present a method for choosing a baseline according to a neutrality value: as a parameter selected by decision-makers, the point at which their choices are determined by the model predictions being either above or below it. Hence, the proposed baseline is set based on a parameter that depends on the actual use of the model. This procedure stands in contrast to how other baselines are set, i.e. without accounting for how the model is used. We empirically validate our choice of baseline in the context of binary classification tasks, using two datasets: a synthetic dataset and a dataset derived from the financial domain.

Related papers

• On Model Extrapolation in Marginal Shapley Values [0.0]
  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.
  arXiv  Detail & Related papers  (2024-12-17T18:33:14Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable. We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions.<n>We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance.<n>Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• Optimal Baseline Corrections for Off-Policy Contextual Bandits [61.740094604552475]
  We aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. We propose a single framework built on their equivalence in learning scenarios. Our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it.
  arXiv  Detail & Related papers  (2024-05-09T12:52:22Z)
• Variational Shapley Network: A Probabilistic Approach to Self-Explaining Shapley values with Uncertainty Quantification [2.6699011287124366]
  Shapley values have emerged as a foundational tool in machine learning (ML) for elucidating model decision-making processes. We introduce a novel, self-explaining method that simplifies the computation of Shapley values significantly, requiring only a single forward pass.
  arXiv  Detail & Related papers  (2024-02-06T18:09:05Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• 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)
• The Optimal Input-Independent Baseline for Binary Classification: The Dutch Draw [0.0]
  The goal of this paper is to examine all baseline methods that are independent of feature values. By identifying which baseline models are optimal, a crucial selection decision in the evaluation process is simplified.
  arXiv  Detail & Related papers  (2023-01-09T13:11:59Z)
• Deep Learning for the Benes Filter [91.3755431537592]
  We present a new numerical method based on the mesh-free neural network representation of the density of the solution of the Benes model. We discuss the role of nonlinearity in the filtering model equations for the choice of the domain of the neural network.
  arXiv  Detail & Related papers  (2022-03-09T14:08:38Z)
• 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)
• On Baselines for Local Feature Attributions [6.700433100198165]
  Local feature attribution methods help to explain black box models. Most attribution models compare the importance of input features with a reference value, often called baseline. Recent studies show that the baseline can heavily impact the quality of feature attributions.
  arXiv  Detail & Related papers  (2021-01-04T11:48:42Z)
• 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)
• Decision-Making with Auto-Encoding Variational Bayes [71.44735417472043]
  We show that a posterior approximation distinct from the variational distribution should be used for making decisions. Motivated by these theoretical results, we propose learning several approximate proposals for the best model. In addition to toy examples, we present a full-fledged case study of single-cell RNA sequencing.
  arXiv  Detail & Related papers  (2020-02-17T19:23:36Z)

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.