Cover Image

When Can You Trust Your Explanations? A Robustness Analysis on Feature Importances

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vascotto, Ilaria, Rodriguez, Alex, Bonaita, Alessandro, Bortolussi, Luca
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Assessing reliability of explanations in unbalanced datasets: a use-case on the occurrence of frost events
by: Vascotto, Ilaria, et al.
Published: (2025)

Retrieval-Augmented Mining of Temporal Logic Specifications from Data
by: Saveri, Gaia, et al.
Published: (2024)

Aggregate Models, Not Explanations: Improving Feature Importance Estimation
by: Paillard, Joseph, et al.
Published: (2026)

Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations
by: Marzari, Luca, et al.
Published: (2024)

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

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

Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes Responses
by: Cahyono, Joshua Adrian, et al.
Published: (2025)

Why Change Your Controller When You Can Change Your Planner: Drag-Aware Trajectory Generation for Quadrotor Systems
by: Zhang, Hanli, et al.
Published: (2024)

Adaptive Experimentation When You Can't Experiment
by: Zhao, Yao, et al.
Published: (2024)

On the Robustness of Global Feature Effect Explanations
by: Baniecki, Hubert, et al.
Published: (2024)

You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning
by: Yang, Tianmeng, et al.
Published: (2024)

Timeseria: an object-oriented time series processing library
by: Russo, Stefano Alberto, et al.
Published: (2024)

Graph-Conditional Flow Matching for Relational Data Generation
by: Scassola, Davide, et al.
Published: (2025)

Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations
by: Basile, Lorenzo, et al.
Published: (2024)

On the Robustness of Bayesian Neural Networks to Adversarial Attacks
by: Bortolussi, Luca, et al.
Published: (2022)

Knowing What You Cannot Explain: Learning to Reject Low-Quality Explanations
by: Stradiotti, Luca, et al.
Published: (2025)

What Can You Do When You Have Zero Rewards During RL?
by: Prakash, Jatin, et al.
Published: (2025)

Fast ML-driven Analog Circuit Layout using Reinforcement Learning and Steiner Trees
by: Basso, Davide, et al.
Published: (2024)

When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning
by: Niu, Haoyi, et al.
Published: (2022)

Frequency maps reveal the correlation between Adversarial Attacks and Implicit Bias
by: Basile, Lorenzo, et al.
Published: (2023)

Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows
by: Sharma, Ramansh, et al.
Published: (2026)

RobustX: Robust Counterfactual Explanations Made Easy
by: Jiang, Junqi, et al.
Published: (2025)

Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation
by: Verdù, Federico Julian Camerota, et al.
Published: (2024)

ECATS: Explainable-by-design concept-based anomaly detection for time series
by: Ferfoglia, Irene, et al.
Published: (2024)

Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints
by: Scassola, Davide, et al.
Published: (2023)

When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
by: Escamilla, Jose Efraim Aguilar, et al.
Published: (2026)

Know When You're Wrong: Aligning Confidence with Correctness for LLM Error Detection
by: Xiaohu, Xie, et al.
Published: (2026)

Robust Explanations for User Trust in Enterprise NLP Systems
by: Zhang, Guilin, et al.
Published: (2026)

Guided by Stars: Interpretable Concept Learning Over Time Series via Temporal Logic Semantics
by: Ferfoglia, Irene, et al.
Published: (2025)

Towards Interpretable Concept Learning over Time Series via Temporal Logic Semantics
by: Ferfoglia, Irene, et al.
Published: (2025)

Your Code Agent Can Grow Alongside You with Structured Memory
by: Deng, Yi-Xuan, et al.
Published: (2026)

Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation
by: Miglior, Luca, et al.
Published: (2025)

When Can You Get Away with Low Memory Adam?
by: Kalra, Dayal Singh, et al.
Published: (2025)

OptiGradTrust: Byzantine-Robust Federated Learning with Multi-Feature Gradient Analysis and Reinforcement Learning-Based Trust Weighting
by: Karami, Mohammad, et al.
Published: (2025)

Cross-Model Consistency of Feature Importance in Electrospinning: Separating Robust from Model-Dependent Features
by: Mahdian, Mehrab, et al.
Published: (2026)

When to Trust Your Data: Enhancing Dyna-Style Model-Based Reinforcement Learning With Data Filter
by: Li, Yansong, et al.
Published: (2024)

Blending adversarial training and representation-conditional purification via aggregation improves adversarial robustness
by: Ballarin, Emanuele, et al.
Published: (2023)

Advancing Routing-Awareness in Analog ICs Floorplanning
by: Basso, Davide, et al.
Published: (2025)

CoCAI: Copula-based Conformal Anomaly Identification for Multivariate Time-Series
by: Pearson, Nicholas A., et al.
Published: (2025)