On Locality of Local Explanation Models

• URL: http://arxiv.org/abs/2106.14648v1
• Date: Thu, 24 Jun 2021 16:20:38 GMT
• Title: On Locality of Local Explanation Models
• Authors: Sahra Ghalebikesabi, Lucile Ter-Minassian, Karla Diaz-Ordaz and Chris Holmes
• Abstract summary: We consider the formulation of neighbourhood reference distributions that improve the local interpretability of Shapley values. We observe that Neighbourhood Shapley values identify meaningful sparse feature relevance attributions that provide insight into local model behaviour.
• Score: 0.43012765978447565
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Shapley values provide model agnostic feature attributions for model outcome at a particular instance by simulating feature absence under a global population distribution. The use of a global population can lead to potentially misleading results when local model behaviour is of interest. Hence we consider the formulation of neighbourhood reference distributions that improve the local interpretability of Shapley values. By doing so, we find that the Nadaraya-Watson estimator, a well-studied kernel regressor, can be expressed as a self-normalised importance sampling estimator. Empirically, we observe that Neighbourhood Shapley values identify meaningful sparse feature relevance attributions that provide insight into local model behaviour, complimenting conventional Shapley analysis. They also increase on-manifold explainability and robustness to the construction of adversarial classifiers.

Related papers

• VARSHAP: Addressing Global Dependency Problems in Explainable AI with Variance-Based Local Feature Attribution [3.545940115969205]
  Existing feature attribution methods like SHAP often suffer from global dependence, failing to capture true local model behavior.<n>This paper introduces VARSHAP, a novel model-agnostic local feature attribution method which uses the reduction of prediction variance as the key importance metric of features.
  arXiv  Detail & Related papers  (2025-06-08T17:26:47Z)
• 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)
• 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)
• Identifiable Latent Neural Causal Models [82.14087963690561]
  Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
  arXiv  Detail & Related papers  (2024-03-23T04:13:55Z)
• Aggregation Weighting of Federated Learning via Generalization Bound Estimation [65.8630966842025]
  Federated Learning (FL) typically aggregates client model parameters using a weighting approach determined by sample proportions. We replace the aforementioned weighting method with a new strategy that considers the generalization bounds of each local model.
  arXiv  Detail & Related papers  (2023-11-10T08:50:28Z)
• Enhanced Local Explainability and Trust Scores with Random Forest Proximities [0.9423257767158634]
  We exploit the fact that any random forest (RF) regression and classification model can be mathematically formulated as an adaptive weighted K nearest-neighbors model. We show that this linearity facilitates a local notion of explainability of RF predictions that generates attributions for any model prediction across observations in the training set. We show how this proximity-based approach to explainability can be used in conjunction with SHAP to explain not just the model predictions, but also out-of-sample performance.
  arXiv  Detail & Related papers  (2023-10-19T02:42:20Z)
• 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)
• Adversarial robustness of sparse local Lipschitz predictors [12.525959293825318]
  This work studies the adversarial robustness of parametric functions composed of a linear predictor and a non-linear representation map. We use sparse local Lipschitzness to better capture the stability and reduced effective dimensionality of predictors upon local perturbations.
  arXiv  Detail & Related papers  (2022-02-26T19:48:07Z)
• A likelihood approach to nonparametric estimation of a singular distribution using deep generative models [4.329951775163721]
  We investigate a likelihood approach to nonparametric estimation of a singular distribution using deep generative models. We prove that a novel and effective solution exists by perturbing the data with an instance noise. We also characterize the class of distributions that can be efficiently estimated via deep generative models.
  arXiv  Detail & Related papers  (2021-05-09T23:13:58Z)
• Goal-oriented adaptive sampling under random field modelling of response probability distributions [0.6445605125467573]
  We consider cases where the spatial variation of response distributions does not only concern their mean and/or variance but also other features including for instance shape or uni-modality versus multi-modality. Our contributions build upon a non-parametric Bayesian approach to modelling the thereby induced fields of probability distributions.
  arXiv  Detail & Related papers  (2021-02-15T15:55:23Z)
• Generalization Properties of Optimal Transport GANs with Latent Distribution Learning [52.25145141639159]
  We study how the interplay between the latent distribution and the complexity of the pushforward map affects performance. Motivated by our analysis, we advocate learning the latent distribution as well as the pushforward map within the GAN paradigm.
  arXiv  Detail & Related papers  (2020-07-29T07:31:33Z)
• Estimating Generalization under Distribution Shifts via Domain-Invariant Representations [75.74928159249225]
  We use a set of domain-invariant predictors as a proxy for the unknown, true target labels. The error of the resulting risk estimate depends on the target risk of the proxy model.
  arXiv  Detail & Related papers  (2020-07-06T17:21:24Z)
• Nonparametric Score Estimators [49.42469547970041]
  Estimating the score from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models. We provide a unifying view of these estimators under the framework of regularized nonparametric regression. We propose score estimators based on iterative regularization that enjoy computational benefits from curl-free kernels and fast convergence.
  arXiv  Detail & Related papers  (2020-05-20T15:01:03Z)
• From interpretability to inference: an estimation framework for universal approximators [0.0]
  We present a novel framework for estimation and inference with the broad class of universal approximators. Inference relies on analyzing the bias and variance properties of individual Shapley components.
  arXiv  Detail & Related papers  (2019-03-11T10:37:05Z)

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.