RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution

• URL: http://arxiv.org/abs/2605.15154v1
• Date: Thu, 14 May 2026 17:51:09 GMT
• Title: RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution
• Abstract summary: This paper proposes a framework for incorporating predictive nature of feature attribution and a robust attribution metric, RoSHAP, for stable feature ranking based on the SHAP metric.<n>We show that, under regularity conditions, the aggregated feature attribution score is Gaussian, which greatly reduces the computational cost of distribution estimation.<n>The RoSHAP approach improves the stability and interpretability of machine learning models, enabling reliable and consistent insights for analysis.
• Score: 10.49574311383701
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attribution measures often exhibit stochastic variation: different train--test splits, random seeds, or model-fitting procedures can produce substantially different attribution values and feature rankings. This paper proposes a framework for incorporating stochastic nature of feature attribution and a robust attribution metric, RoSHAP, for stable feature ranking based on the SHAP metric. The proposed framework models the distribution of feature attribution scores and estimates it through bootstrap resampling and kernel density estimation. We show that, under mild regularity conditions, the aggregated feature attribution score is asymptotically Gaussian, which greatly reduces the computational cost of distribution estimation. The RoSHAP summarizes the distribution of SHAP into a robust feature-ranking criterion that simultaneously rewards features that are active, strong, and stable. Through simulations and real-data experiments, the proposed framework and RoSHAP outperform standard single-run attribution measures in identifying signal features. In addition, models built using RoSHAP-selected features achieve predictive performance comparable to full-feature models while using substantially fewer predictors. The proposed RoSHAP approach improves the stability and interpretability of machine learning models, enabling reliable and consistent insights for analysis.

Related papers

• Robust model-based clustering via mixtures of multivariate pseudo-Voigt distributions [0.0]
  A weighted convex combination of Gaussian and Cauchy distributions is proposed for robust model-based clustering and outlier detection.<n>The framework is shown to be particularly effective for data characterized by heavy-tailed behavior.
  arXiv  Detail & Related papers  (2026-08-27T18:38:42Z)
• Joint Model and Data Sparsification via the Marginal Likelihood [53.29070892356214]
  We propose jointly learning individual feature and sample relevancies, enabling simultaneous model and data sparsification.<n>This symmetric pruning of model and data offers a natural extension that preserves conjugacy.<n> Empirical results across diverse regression tasks affirm that a joint ARD approach consistently yields both sparse and robust prediction models.
  arXiv  Detail & Related papers  (2026-05-28T13:26:53Z)
• Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition [0.876171257490837]
  We propose a novel metric aimed at assessing the consistency of model explanations.<n>We implement this metric using a pre-trained BERT model on the SST-2 sentiment analysis dataset.<n>We evaluate the ability of this metric to identify misaligned predictions and inconsistencies in model explanations.
  arXiv  Detail & Related papers  (2026-04-06T06:05:21Z)
• Distributional Evaluation of Generative Models via Relative Density Ratio [12.663086000741872]
  We propose a functional evaluation metric for generative models based on the relative density ratio (RDR)<n>We show that the RDR as a functional summary of the goodness-of-fit for the generative model, possesses several desirable theoretical properties.<n>We show that the estimated RDR not only allows for an effective comparison of the overall performance of competing generative models, but it can also offer a convenient means of revealing the nature of the underlying goodness-of-fit.
  arXiv  Detail & Related papers  (2025-10-29T13:31:35Z)
• Model Correlation Detection via Random Selection Probing [62.093777777813756]
  Existing similarity-based methods require access to model parameters or produce scores without thresholds.<n>We introduce Random Selection Probing (RSP), a hypothesis-testing framework that formulates model correlation detection as a statistical test.<n>RSP produces rigorous p-values that quantify evidence of correlation.
  arXiv  Detail & Related papers  (2025-09-29T01:40:26Z)
• The Lie of the Average: How Class Incremental Learning Evaluation Deceives You? [48.83567710215299]
  Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones.<n>We argue that a robust CIL evaluation protocol should accurately characterize and estimate the entire performance distribution.<n>We propose EDGE, an evaluation protocol that adaptively identifies and samples extreme class sequences using inter-task similarity.
  arXiv  Detail & Related papers  (2025-09-26T17:00:15Z)
• SHAP-Guided Regularization in Machine Learning Models [1.0515439489916734]
  We propose a SHAP-guided regularization framework that incorporates feature importance constraints into model training to enhance both predictive performance and interpretability.<n>Our approach applies entropy-based penalties to encourage sparse, concentrated feature attributions while promoting stability across samples.
  arXiv  Detail & Related papers  (2025-07-31T15:45:38Z)
• Model averaging in the space of probability distributions [0.0]
  We study aggregation schemes in the space of probability distributions metrized in terms of the Wasserstein distance.<n>We employ regularization schemes motivated by the standard elastic net penalization, which is shown to consistently yield models enjoying sparsity properties.<n>The proposed approach is applied to a real-world dataset of insurance losses to estimate the claim size distribution and the associated tail risk.
  arXiv  Detail & Related papers  (2025-07-15T20:41:57Z)
• Value-Distributional Model-Based Reinforcement Learning [59.758009422067]
  Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective. We propose Epistemic Quantile-Regression (EQR), a model-based algorithm that learns a value distribution function.
  arXiv  Detail & Related papers  (2023-08-12T14:59:19Z)
• Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees [57.67528738886731]
  We study the numerical stability of scalable sparse approximations based on inducing points. For low-dimensional tasks such as geospatial modeling, we propose an automated method for computing inducing points satisfying these conditions.
  arXiv  Detail & Related papers  (2022-10-14T15:20:17Z)
• Distributional Robustness and Regularization in Reinforcement Learning [62.23012916708608]
  We introduce a new regularizer for empirical value functions and show that it lower bounds the Wasserstein distributionally robust value function. It suggests using regularization as a practical tool for dealing with $textitexternal uncertainty$ in reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-05T19:56:23Z)

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.