Cover Image

How to safely discard features based on aggregate SHAP values

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bhattacharjee, Robi, Frohnapfel, Karolin, von Luxburg, Ulrike
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Informative Post-Hoc Explanations Only Exist for Simple Functions
by: Günther, Eric, et al.
Published: (2025)

Auditing Local Explanations is Hard
by: Bhattacharjee, Robi, et al.
Published: (2024)

Using predictive multiplicity to measure individual performance within the AI Act
by: Frohnapfel, Karolin, et al.
Published: (2026)

How Much Can We Forget about Data Contamination?
by: Bordt, Sebastian, et al.
Published: (2024)

On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
by: Haas, Moritz, et al.
Published: (2025)

SHAP-based Explanations are Sensitive to Feature Representation
by: Hwang, Hyunseung, et al.
Published: (2025)

PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
by: Fumagalli, Fabian, et al.
Published: (2026)

Interaction Tensor SHAP
by: Hasegawa, Hiroki, et al.
Published: (2025)

Iterative missing value imputation based on feature importance
by: Guo, Cong, et al.
Published: (2023)

Towards trustable SHAP scores
by: Letoffe, Olivier, et al.
Published: (2024)

CS-SHAP: Extending SHAP to Cyclic-Spectral Domain for Better Interpretability of Intelligent Fault Diagnosis
by: Chen, Qian, et al.
Published: (2025)

Explanation Multiplicity in SHAP: Characterization and Assessment
by: Hwang, Hyunseung, et al.
Published: (2026)

Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAP
by: Sovrano, Francesco
Published: (2025)

From SHAP Scores to Feature Importance Scores
by: Letoffe, Olivier, et al.
Published: (2024)

On the Tractability of SHAP Explanations under Markovian Distributions
by: Marzouk, Reda, et al.
Published: (2024)

Towards Piece-by-Piece Explanations for Chess Positions with SHAP
by: Spinnato, Francesco
Published: (2025)

ContextualSHAP : Enhancing SHAP Explanations Through Contextual Language Generation
by: Dwiyanti, Latifa, et al.
Published: (2025)

HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization
by: Wever, Marcel, et al.
Published: (2025)

SHAP scores fail pervasively even when Lipschitz succeeds
by: Letoffe, Olivier, et al.
Published: (2024)

A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME
by: Salih, Ahmed, et al.
Published: (2023)

A Polynomial-Time Axiomatic Alternative to SHAP for Feature Attribution
by: Hiraki, Kazuhiro, et al.
Published: (2026)

A feature selection method based on Shapley values robust to concept shift in regression
by: Sebastián, Carlos, et al.
Published: (2023)

CQD-SHAP: Explainable Complex Query Answering via Shapley Values
by: Abbasi, Parsa, et al.
Published: (2025)

Enhancing SHAP Explainability for Diagnostic and Prognostic ML Models in Alzheimer Disease
by: Guillén, Pablo, et al.
Published: (2026)

KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions
by: Fumagalli, Fabian, et al.
Published: (2024)

Fooling SHAP with Output Shuffling Attacks
by: Yuan, Jun, et al.
Published: (2024)

Rethinking Explainable Machine Learning as Applied Statistics
by: Bordt, Sebastian, et al.
Published: (2024)

Disentangling Interactions and Dependencies in Feature Attribution
by: König, Gunnar, et al.
Published: (2024)

DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values
by: Kim, Changhun, et al.
Published: (2025)

Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection
by: Kelodjou, Gwladys, et al.
Published: (2023)

CNN-TFT explained by SHAP with multi-head attention weights for time series forecasting
by: Stefenon, Stefano F., et al.
Published: (2025)

TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
by: Heidari, Farzaneh, et al.
Published: (2026)

Choose Your Explanation: A Comparison of SHAP and GradCAM in Human Activity Recognition
by: Tempel, Felix, et al.
Published: (2024)

Causal SHAP: Feature Attribution with Dependency Awareness through Causal Discovery
by: Ng, Woon Yee, et al.
Published: (2025)

Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
by: Kong, Lingxiao, et al.
Published: (2026)

Dual feature-based and example-based explanation methods
by: Konstantinov, Andrei V., et al.
Published: (2024)

MAML-KT: Addressing Cold Start Problem in Knowledge Tracing for New Students via Few-Shot Model-Agnostic Meta Learning
by: Bhattacharjee, Indronil, et al.
Published: (2026)

Onboard Out-of-Calibration Detection of Deep Learning Models using Conformal Prediction
by: Bhattacharjee, Protim, et al.
Published: (2024)

FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation
by: Zhu, Lin, et al.
Published: (2025)

Interpreting Time Series Forecasts with LIME and SHAP: A Case Study on the Air Passengers Dataset
by: Shukla, Manish
Published: (2025)