Copertina

Measuring Leakage in Concept-Based Methods: An Information Theoretic Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Makonnen, Mikael, Vandenhirtz, Moritz, Laguna, Sonia, Vogt, Julia E
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Stochastic Concept Bottleneck Models
di: Vandenhirtz, Moritz, et al.
Pubblicazione: (2024)

Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
di: Laguna, Sonia, et al.
Pubblicazione: (2024)

Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks
di: Carballo-Castro, Alba, et al.
Pubblicazione: (2024)

Post-hoc Stochastic Concept Bottleneck Models
di: Hoffmann, Wiktor Jan, et al.
Pubblicazione: (2025)

From Logits to Hierarchies: Hierarchical Clustering made Simple
di: Palumbo, Emanuele, et al.
Pubblicazione: (2024)

Foundation Model for Cardiac Time Series via Masked Latent Attention
di: Vandenhirtz, Moritz, et al.
Pubblicazione: (2026)

Leakage and Interpretability in Concept-Based Models
di: Parisini, Enrico, et al.
Pubblicazione: (2025)

From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
di: Vandenhirtz, Moritz, et al.
Pubblicazione: (2025)

Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learning
di: Sun, Ao, et al.
Pubblicazione: (2024)

Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion
di: Laguna, Sonia, et al.
Pubblicazione: (2026)

On Information-Theoretic Measures of Predictive Uncertainty
di: Schweighofer, Kajetan, et al.
Pubblicazione: (2024)

Information-Theoretic Safe Bayesian Optimization
di: Bottero, Alessandro G., et al.
Pubblicazione: (2024)

Loss Given Default Prediction Under Measurement-Induced Mixture Distributions: An Information-Theoretic Approach
di: Marín, Javier
Pubblicazione: (2025)

An Information Theoretic Approach to Machine Unlearning
di: Foster, Jack, et al.
Pubblicazione: (2024)

Interpretable Reward Modeling with Active Concept Bottlenecks
di: Laguna, Sonia, et al.
Pubblicazione: (2025)

Interpretable Diffusion Models with B-cos Networks
di: Bernold, Nicola, et al.
Pubblicazione: (2025)

scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data
di: Vandenhirtz, Moritz, et al.
Pubblicazione: (2024)

On Leakage in Machine Learning Pipelines
di: Sasse, Leonard, et al.
Pubblicazione: (2023)

Reference-Guided Machine Unlearning
di: Mirlach, Jonas, et al.
Pubblicazione: (2026)

Two Is Better Than One: Aligned Representation Pairs for Anomaly Detection
di: Ryser, Alain, et al.
Pubblicazione: (2024)

Information-Theoretic Policy Pre-Training with Empowerment
di: Schneider, Moritz, et al.
Pubblicazione: (2025)

Rethinking Evaluation in the Era of Time Series Foundation Models: (Un)known Information Leakage Challenges
di: Meyer, Marcel, et al.
Pubblicazione: (2025)

Probing the Information Theoretical Roots of Spatial Dependence Measures
di: Wang, Zhangyu, et al.
Pubblicazione: (2024)

Can We Formally Verify Neural PDE Surrogates? SMT Compilation of Small Fourier Neural Operators
di: Baheri, Ali, et al.
Pubblicazione: (2026)

Benchmarking the Fairness of Image Upsampling Methods
di: Laszkiewicz, Mike, et al.
Pubblicazione: (2024)

Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach
di: Lu, Ziqing, et al.
Pubblicazione: (2025)

Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
di: Zarlenga, Mateo Espinosa, et al.
Pubblicazione: (2025)

Information-Theoretic Foundations for Machine Learning
di: Jeon, Hong Jun, et al.
Pubblicazione: (2024)

Measure-Theoretic Anti-Causal Representation Learning
di: Behnam, Arman, et al.
Pubblicazione: (2025)

Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theory
di: Zhang, Xiaojin, et al.
Pubblicazione: (2024)

A survey on Concept-based Approaches For Model Improvement
di: Gupta, Avani, et al.
Pubblicazione: (2024)

A Concept-Centric Approach to Multi-Modality Learning
di: Geng, Yuchong, et al.
Pubblicazione: (2024)

Transformer Injectivity & Geometric Robustness - Analytic Margins and Bi-Lipschitz Uniformity of Sequence-Level Hidden States
di: von Strauss, Mikael
Pubblicazione: (2025)

Measuring the (Un)Faithfulness of Concept-Based Explanations
di: Kumar, Shubham, et al.
Pubblicazione: (2025)

Survival Concept-Based Learning Models
di: Kirpichenko, Stanislav R., et al.
Pubblicazione: (2025)

Interpretable Concept-Based Memory Reasoning
di: Debot, David, et al.
Pubblicazione: (2024)

An Information Theoretic Evaluation Metric For Strong Unlearning
di: Jeon, Dongjae, et al.
Pubblicazione: (2024)

Information-Theoretic Foundations for Neural Scaling Laws
di: Jeon, Hong Jun, et al.
Pubblicazione: (2024)

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
di: Oh, Changdae, et al.
Pubblicazione: (2025)

ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks
di: Mu, Xinyu, et al.
Pubblicazione: (2025)