Regional Explanations: Bridging Local and Global Variable Importance

• URL: http://arxiv.org/abs/2604.11223v1
• Date: Mon, 13 Apr 2026 09:24:58 GMT
• Title: Regional Explanations: Bridging Local and Global Variable Importance
• Abstract summary: We argue that a sound local attribution method should not assign importance to features that neither influence the model output nor exhibit statistical dependence with functionality-relevant features.<n>We propose R-LOCO, which bridges the gap between local and global explanations and provides more accurate attributions.
• Score: 5.8153681798663
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We analyze two widely used local attribution methods, Local Shapley Values and LIME, which aim to quantify the contribution of a feature value $x_i$ to a specific prediction $f(x_1, \dots, x_p)$. Despite their widespread use, we identify fundamental limitations in their ability to reliably detect locally important features, even under ideal conditions with exact computations and independent features. We argue that a sound local attribution method should not assign importance to features that neither influence the model output (e.g., features with zero coefficients in a linear model) nor exhibit statistical dependence with functionality-relevant features. We demonstrate that both Local SV and LIME violate this fundamental principle. To address this, we propose R-LOCO (Regional Leave Out COvariates), which bridges the gap between local and global explanations and provides more accurate attributions. R-LOCO segments the input space into regions with similar feature importance characteristics. It then applies global attribution methods within these regions, deriving an instance's feature contributions from its regional membership. This approach delivers more faithful local attributions while avoiding local explanation instability and preserving instance-specific detail often lost in global methods.

Related papers

• Efficiency Follows Global-Local Decoupling [62.05489838893081]
  We introduce ConvNeur, a two-branch architecture in which a lightweight neural memory branch aggregates global context on a compact set of tokens.<n>A learned gate lets global cues modulate local features without entangling their objectives.<n>On standard classification, detection, and segmentation benchmarks, ConvNeur matches or surpasses comparable alternatives at similar or lower compute.
  arXiv  Detail & Related papers  (2026-03-20T02:20:16Z)
• GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations [10.111546558028271]
  Feature-based explanation methods aim to quantify how features influence the model's behavior, either locally or globally, but different methods often disagree.<n>We propose a generalized regional explanation framework that partitions the feature space into regions where interaction and distribution influences are minimized.<n>We demonstrate its effectiveness on real-world datasets, providing a practical tool for consistent and interpretable feature explanations.
  arXiv  Detail & Related papers  (2026-01-30T09:49:26Z)
• Provable Recovery of Locally Important Signed Features and Interactions from Random Forest [0.0]
  In many domains, such as personalized medicine, local interpretations for individual predictions are often required.<n>We propose a novel, local, model-specific FII method that identifies frequent co-occurrences of features along decision paths.<n>We prove that our method consistently recovers the true local signal features and their interactions under a Locally Spike Sparse (LSS) model.
  arXiv  Detail & Related papers  (2025-12-11T19:53:15Z)
• 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)
• Model agnostic local variable importance for locally dependent relationships [2.3374134413353254]
  We propose a new model-agnostic method for calculating local variable importance, CLIQUE, that captures locally dependent relationships.<n>We show that CLIQUE emphasizes locally dependent information and properly reduces bias in regions where variables do not affect the response.
  arXiv  Detail & Related papers  (2024-11-13T17:59:44Z)
• Guarantee Regions for Local Explanations [29.429229877959663]
  We propose an anchor-based algorithm for identifying regions in which local explanations are guaranteed to be correct. Our method produces an interpretable feature-aligned box where the prediction of the local surrogate model is guaranteed to match the predictive model.
  arXiv  Detail & Related papers  (2024-02-20T06:04:44Z)
• Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition [54.334773598942775]
  Domain shift poses a significant challenge in Cross-Domain Facial Expression Recognition (CD-FER) We propose an Adaptive Global-Local Representation Learning and Selection framework.
  arXiv  Detail & Related papers  (2024-01-20T02:21:41Z)
• Change Detection for Local Explainability in Evolving Data Streams [72.4816340552763]
  Local feature attribution methods have become a popular technique for post-hoc and model-agnostic explanations. It is often unclear how local attributions behave in realistic, constantly evolving settings such as streaming and online applications. We present CDLEEDS, a flexible and model-agnostic framework for detecting local change and concept drift.
  arXiv  Detail & Related papers  (2022-09-06T18:38:34Z)
• Federated and Generalized Person Re-identification through Domain and Feature Hallucinating [88.77196261300699]
  We study the problem of federated domain generalization (FedDG) for person re-identification (re-ID) We propose a novel method, called "Domain and Feature Hallucinating (DFH)", to produce diverse features for learning generalized local and global models. Our method achieves the state-of-the-art performance for FedDG on four large-scale re-ID benchmarks.
  arXiv  Detail & Related papers  (2022-03-05T09:15:13Z)
• An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning [77.72330187258498]
  We propose a novel Entropy-guided Reinforced Partial Convolutional Network (ERPCNet) ERPCNet extracts and aggregates localities based on semantic relevance and visual correlations without human-annotated regions. It not only discovers global-cooperative localities dynamically but also converges faster for policy gradient optimization.
  arXiv  Detail & Related papers  (2021-11-03T11:13:13Z)
• LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts [65.79931333193016]
  We present a novel Local-Region-Context Network (LRC-Net) to learn discriminative features on point clouds. LRC-Net encodes fine-grained contexts inside and among local regions simultaneously. Results show LRC-Net is competitive with state-of-the-art methods in shape classification and shape segmentation applications.
  arXiv  Detail & Related papers  (2020-03-18T14:34:08Z)

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.