When Feature Representation Changes Local Explanations: A Controlled Comparison of SHAP and LIME under Numerical Discretization

Local feature attributions are computed over a feature representation chosen by an upstream data-engineering step, yet they are read as statements about the underlying quantity. We ask how discretizing one continuous feature changes local KernelSHAP and LIME explanations when the classifier is held fixed, and whether the two explainers respond differently. A random forest is trained on UCI Adult and frozen; age is collapsed onto equi-width or quantile bin representatives (k in {3,5,10}) before the model receives it, and the same 120 held-out instances are explained in every condition across multiple seeds. We show analytically and numerically that for KernelSHAP this is exactly equivalent to explaining the unchanged model at the quantized instance against a quantized background, so the comparison is between two effective inputs rather than a pure explainer effect; for LIME no such equivalence holds. Each attribution change is compared with a seed-noise floor from re-running the explainer on the unchanged condition. KernelSHAP's age attribution exceeds its noise floor in all 6 pre-specified conditions (median ratios 2.4-59, all significant after Holm correction); on the raw scale LIME's exceeds its floor in only 2 of 6 and in the rest is no larger than its own run-to-run variation. SHAP's normalized change exceeds LIME's in every condition (rank-biserial 0.81-1.00), while LIME is 2.5-4.6x less consistent across repeats. Predicted classes change for only 0.8-5.8% of instances and held-out ROC-AUC never falls below 0.9097, yet 45-94% of instances show a large SHAP attribution change with no class flip. Feature-importance rankings barely move (median Spearman >= 0.979, top-3 overlap 1.00). The representation change and the change in effective input cannot be separated within a frozen-model design.

Authors

Institutions

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.21159
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

When Feature Representation Changes Local Explanations: A Controlled Comparison of SHAP and LIME under Numerical Discretization

Parv Patel
arXiv (Cornell University)
Explainable Artificial Intelligence (XAI)
preprint

When Feature Representation Changes Local Explanations: A Controlled Comparison of SHAP and LIME under Numerical Discretization

Parv Patel
preprint en

Abstract

Local feature attributions are computed over a feature representation chosen by an upstream data-engineering step, yet they are read as statements about the underlying quantity. We ask how discretizing one continuous feature changes local KernelSHAP and LIME explanations when the classifier is held fixed, and whether the two explainers respond differently. A random forest is trained on UCI Adult and frozen; age is collapsed onto equi-width or quantile bin representatives (k in {3,5,10}) before the model receives it, and the same 120 held-out instances are explained in every condition across multiple seeds. We show analytically and numerically that for KernelSHAP this is exactly equivalent to explaining the unchanged model at the quantized instance against a quantized background, so the comparison is between two effective inputs rather than a pure explainer effect; for LIME no such equivalence holds. Each attribution change is compared with a seed-noise floor from re-running the explainer on the unchanged condition. KernelSHAP's age attribution exceeds its noise floor in all 6 pre-specified conditions (median ratios 2.4-59, all significant after Holm correction); on the raw scale LIME's exceeds its floor in only 2 of 6 and in the rest is no larger than its own run-to-run variation. SHAP's normalized change exceeds LIME's in every condition (rank-biserial 0.81-1.00), while LIME is 2.5-4.6x less consistent across repeats. Predicted classes change for only 0.8-5.8% of instances and held-out ROC-AUC never falls below 0.9097, yet 45-94% of instances show a large SHAP attribution change with no class flip. Feature-importance rankings barely move (median Spearman >= 0.979, top-3 overlap 1.00). The representation change and the change in effective input cannot be separated within a frozen-model design.

arXiv (Cornell University)
Indian Institute of Technology Palakkad (IN)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon