Imagen de Portada

SHAP-based Explanations are Sensitive to Feature Representation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hwang, Hyunseung, Bell, Andrew, Fonseca, Joao, Pliatsika, Venetia, Stoyanovich, Julia, Whang, Steven Euijong
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

ShaRP: Explaining Rankings and Preferences with Shapley Values
por: Pliatsika, Venetia, et al.
Publicado: (2024)

Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs
por: Fonseca, Joao, et al.
Publicado: (2025)

ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations
por: Fonseca, Joao, et al.
Publicado: (2026)

GradMix: Gradient-based Selective Mixup for Robust Data Augmentation in Class-Incremental Learning
por: Kim, Minsu, et al.
Publicado: (2025)

Fair Class-Incremental Learning using Sample Weighting
por: Park, Jaeyoung, et al.
Publicado: (2024)

PFGuard: A Generative Framework with Privacy and Fairness Safeguards
por: Kim, Soyeon, et al.
Publicado: (2024)

PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
por: Lee, Jaejun, et al.
Publicado: (2024)

MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning
por: Hwang, Seong-Hyeon, et al.
Publicado: (2025)

ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models
por: Oh, Jio, et al.
Publicado: (2024)

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

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

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

T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning
por: Hwang, Seong-Hyeon, et al.
Publicado: (2025)

RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression Tasks
por: Hwang, Seong-Hyeon, et al.
Publicado: (2024)

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

Towards trustable SHAP scores
por: Letoffe, Olivier, et al.
Publicado: (2024)

VirnyFlow: A Design Space for Responsible Model Development
por: Herasymuk, Denys, et al.
Publicado: (2025)

Making Transparency Advocates: An Educational Approach Towards Better Algorithmic Transparency in Practice
por: Bell, Andrew, et al.
Publicado: (2024)

Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers
por: Chung, Chanyoung, et al.
Publicado: (2023)

CAFO: Feature-Centric Explanation on Time Series Classification
por: Kim, Jaeho, et al.
Publicado: (2024)

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

Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion
por: Lee, Jaejun, et al.
Publicado: (2026)

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

LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views
por: Roh, Yuji, et al.
Publicado: (2024)

DeFrame: Debiasing Large Language Models Against Framing Effects
por: Lim, Kahee, et al.
Publicado: (2026)

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

Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity
por: Bell, Andrew, et al.
Publicado: (2024)

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

Interaction Tensor SHAP
por: Hasegawa, Hiroki, et al.
Publicado: (2025)

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

An Epistemic and Aleatoric Decomposition of Arbitrariness to Constrain the Set of Good Models
por: Khan, Falaah Arif, et al.
Publicado: (2023)

A New Paradigm for Counterfactual Reasoning in Fairness and Recourse
por: Bynum, Lucius E. J., et al.
Publicado: (2024)

Still More Shades of Null: An Evaluation Suite for Responsible Missing Value Imputation
por: Khan, Falaah Arif, et al.
Publicado: (2024)

How to safely discard features based on aggregate SHAP values
por: Bhattacharjee, Robi, et al.
Publicado: (2025)

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

Do's and Don'ts: Learning Desirable Skills with Instruction Videos
por: Kim, Hyunseung, et al.
Publicado: (2024)

FORCE: Feature-Oriented Representation with Clustering and Explanation
por: Mukherjee, Rishav, et al.
Publicado: (2025)

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

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