Copertina

Hypothesis Class Determines Explanation: Why Accurate Models Disagree on Feature Attribution

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	B, Thackshanaramana
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation
di: Baer, Gregor, et al.
Pubblicazione: (2025)

EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs
di: Bensmail, Chama
Pubblicazione: (2025)

Provably Better Explanations with Optimized Aggregation of Feature Attributions
di: Decker, Thomas, et al.
Pubblicazione: (2024)

Unifying Attribution-Based Explanations Using Functional Decomposition
di: Gevaert, Arne, et al.
Pubblicazione: (2024)

GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks
di: Sanderson, Jacob, et al.
Pubblicazione: (2026)

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
di: Shao, Shuo, et al.
Pubblicazione: (2024)

Attribution Explanations for Deep Neural Networks: A Theoretical Perspective
di: Deng, Huiqi, et al.
Pubblicazione: (2025)

Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It
di: Tai, Wenxin, et al.
Pubblicazione: (2026)

Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
di: Decker, Thomas, et al.
Pubblicazione: (2025)

Impossibility Theorems for Feature Attribution
di: Bilodeau, Blair, et al.
Pubblicazione: (2022)

LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
di: Sokol, Kacper, et al.
Pubblicazione: (2020)

Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learning
di: Zuo, Rui, et al.
Pubblicazione: (2024)

Probabilistic Stability Guarantees for Feature Attributions
di: Jin, Helen, et al.
Pubblicazione: (2025)

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
di: Achtibat, Reduan, et al.
Pubblicazione: (2022)

Feature-level Interaction Explanations in Multimodal Transformers
di: Kim, Yeji, et al.
Pubblicazione: (2026)

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

Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
di: Bley, Florian, et al.
Pubblicazione: (2025)

Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
di: Gkolemis, Vasilis, et al.
Pubblicazione: (2026)

Class-Dependent Perturbation Effects in Evaluating Time Series Attributions
di: Baer, Gregor, et al.
Pubblicazione: (2025)

On Identifying Why and When Foundation Models Perform Well on Time-Series Forecasting Using Automated Explanations and Rating
di: Widener, Michael, et al.
Pubblicazione: (2025)

On the Properties of Feature Attribution for Supervised Contrastive Learning
di: Arrighi, Leonardo, et al.
Pubblicazione: (2026)

Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies
di: Teufel, Jonas, et al.
Pubblicazione: (2023)

POIFormer: A Transformer-Based Framework for Accurate and Scalable Point-of-Interest Attribution
di: Saxena, Nripsuta Ani, et al.
Pubblicazione: (2025)

FLEX: Feature Importance from Layered Counterfactual Explanations
di: Keshtmand, Nawid, et al.
Pubblicazione: (2025)

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

Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum Flow
di: Azarkhalili, Behrooz, et al.
Pubblicazione: (2025)

Correlation-Aware Feature Attribution Based Explainable AI
di: Sengupta, Poushali, et al.
Pubblicazione: (2025)

DeepACTIF: Efficient Feature Attribution via Activation Traces in Neural Sequence Models
di: Hosp, Benedikt W.
Pubblicazione: (2025)

Hypothesis Testing the Circuit Hypothesis in LLMs
di: Shi, Claudia, et al.
Pubblicazione: (2024)

Scaling Law Hypothesis for Multimodal Model
di: Sun, Qingyun, et al.
Pubblicazione: (2024)

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

Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier
di: Li, Xinpeng, et al.
Pubblicazione: (2025)

A Dual-Perspective Approach to Evaluating Feature Attribution Methods
di: Li, Yawei, et al.
Pubblicazione: (2023)

SHapley Estimated Explanation (SHEP): A Fast Post-Hoc Attribution Method for Interpreting Intelligent Fault Diagnosis
di: Chen, Qian, et al.
Pubblicazione: (2025)

Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
di: Sernau, Luke
Pubblicazione: (2024)

Prospector Heads: Generalized Feature Attribution for Large Models & Data
di: Machiraju, Gautam, et al.
Pubblicazione: (2024)

Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models
di: Ayad, Célia Wafa, et al.
Pubblicazione: (2025)

One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
di: Kasmi, Gabriel, et al.
Pubblicazione: (2024)

Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
di: Schnake, Thomas, et al.
Pubblicazione: (2024)

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution
di: Vu, Kiana, et al.
Pubblicazione: (2024)