Copertina

Feature salience - not task-informativeness - drives machine learning model explanations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Clark, Benedict, Oliveira, Marta, Wilming, Rick, Haufe, Stefan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The effect of whitening on explanation performance
di: Clark, Benedict, et al.
Pubblicazione: (2026)

GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations
di: Wilming, Rick, et al.
Pubblicazione: (2024)

Benchmarking the Influence of Pre-training on Explanation Performance in MR Image Classification
di: Oliveira, Marta, et al.
Pubblicazione: (2023)

Explainable AI needs formalization
di: Haufe, Stefan, et al.
Pubblicazione: (2024)

EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods
di: Clark, Benedict, et al.
Pubblicazione: (2024)

cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context
di: Martin, Jörg, et al.
Pubblicazione: (2026)

Beyond saliency: enhancing explanation of speech emotion recognition with expert-referenced acoustic cues
di: Nasr, Seham, et al.
Pubblicazione: (2025)

A Bayesian explanation of machine learning models based on modes and functional ANOVA
di: Long, Quan
Pubblicazione: (2024)

Generative clinical time series models trained on moderate amounts of patient data are privacy preserving
di: Zhumagambetov, Rustam, et al.
Pubblicazione: (2026)

Minimizing False-Positive Attributions in Explanations of Non-Linear Models
di: Gjølbye, Anders, et al.
Pubblicazione: (2025)

Mockingbird: How does LLM perform in general machine learning tasks?
di: Jia, Haoyu, et al.
Pubblicazione: (2025)

Bridging visual saliency and large language models for explainable deep learning in medical imaging
di: Nguezet, Paul Valery, et al.
Pubblicazione: (2026)

Time series saliency maps: explaining models across multiple domains
di: Kechris, Christodoulos, et al.
Pubblicazione: (2025)

Benchmarking quantum machine learning kernel training for classification tasks
di: Alvarez-Estevez, Diego
Pubblicazione: (2024)

How deep is your network? Deep vs. shallow learning of transfer operators
di: Tabish, Mohammad, et al.
Pubblicazione: (2025)

Differentiable multiphase flow model for physics-informed machine learning in reservoir pressure management
di: Rashid, Harun Ur, et al.
Pubblicazione: (2025)

On GNN explanability with activation rules
di: Veyrin-Forrer, Luca, et al.
Pubblicazione: (2024)

The role of data-induced randomness in quantum machine learning classification tasks
di: Casas, Berta, et al.
Pubblicazione: (2024)

Locating disparities in machine learning
di: von Zahn, Moritz, et al.
Pubblicazione: (2022)

Regularising NARX models with multi-task learning
di: Bee, Sarah, et al.
Pubblicazione: (2025)

Cuffless, calibration-free hemodynamic monitoring with physics-informed machine learning models
di: Crandall, Henry, et al.
Pubblicazione: (2025)

On the good reliability of an interval-based metric to validate prediction uncertainty for machine learning regression tasks
di: Pernot, Pascal
Pubblicazione: (2024)

Evaluating saliency scores in point clouds of natural environments by learning surface anomalies
di: Arav, Reuma, et al.
Pubblicazione: (2024)

On the failure of ReLU activation for physics-informed machine learning
di: Rowan, Conor
Pubblicazione: (2025)

An operator preconditioning perspective on training in physics-informed machine learning
di: De Ryck, Tim, et al.
Pubblicazione: (2023)

Estimating carbon pools in the shelf sea environment: reanalysis or model-informed machine learning?
di: Skakala, Jozef
Pubblicazione: (2025)

Negative impact of heavy-tailed uncertainty and error distributions on the reliability of calibration statistics for machine learning regression tasks
di: Pernot, Pascal
Pubblicazione: (2024)

Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
di: De Ryck, Tim, et al.
Pubblicazione: (2024)

Potential failures of physics-informed machine learning in traffic flow modeling: theoretical and experimental analysis
di: Lei, Yuan-Zheng, et al.
Pubblicazione: (2025)

When to retrain a machine learning model
di: Florence, Regol, et al.
Pubblicazione: (2025)

Understanding with toy surrogate models in machine learning
di: Páez, Andrés
Pubblicazione: (2024)

Hessian-informed machine learning interatomic potential towards bridging theory and experiments
di: Yin, Bangchen, et al.
Pubblicazione: (2026)

Deep multimodal saliency parcellation of cerebellar pathways: linking microstructure and individual function through explainable multitask learning
di: Tchetchenian, Ari, et al.
Pubblicazione: (2024)

Causal machine learning for predicting treatment outcomes
di: Feuerriegel, Stefan, et al.
Pubblicazione: (2024)

Causal hybrid modeling with double machine learning
di: Cohrs, Kai-Hendrik, et al.
Pubblicazione: (2024)

Cross-talk based multi-task learning for fault classification of machine system influenced by multiple variables
di: Yi, Wonjun, et al.
Pubblicazione: (2026)

Beyond single-model XAI: aggregating multi-model explanations for enhanced trustworthiness
di: Vascotto, Ilaria, et al.
Pubblicazione: (2025)

Physics-informed sensor coverage through structure preserving machine learning
di: Shaffer, Benjamin David, et al.
Pubblicazione: (2025)

SeisT: A foundational deep learning model for earthquake monitoring tasks
di: Li, Sen, et al.
Pubblicazione: (2023)

A Physics-informed machine learning model for time-dependent wave runup prediction
di: Naeini, Saeed Saviz, et al.
Pubblicazione: (2024)