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

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

13 April 2025

Mikael Makonnen

Moritz Vandenhirtz

ArXiv (abs)PDF HTML

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

9 / 9 papers shown

Title
Leakage and Interpretability in Concept-Based Models Enrico Parisini Tapabrata Chakraborti Chris Harbron Ben D. MacArthur Christopher R. S. Banerji 116 1 0 18 Apr 2025
Stochastic Concept Bottleneck Models Moritz Vandenhirtz Sonia Laguna Ricards Marcinkevics Julia E. Vogt 77 12 0 27 Jun 2024
Interpretable and intervenable ultrasonography-based machine learning models for pediatric appendicitis Ricards Marcinkevics Patricia Reis Wolfertstetter Ugne Klimiene Kieran Chin-Cheong Alyssia Paschke ... David Niederberger S. Wellmann Ece Ozkan C. Knorr Julia E. Vogt 104 27 0 28 Feb 2023
Promises and Pitfalls of Black-Box Concept Learning Models Anita Mahinpei Justin Clark Isaac Lage Finale Doshi-Velez Weiwei Pan 91 96 0 24 Jun 2021
Do Concept Bottleneck Models Learn as Intended? Andrei Margeloiu Matthew Ashman Umang Bhatt Yanzhi Chen M. Jamnik Adrian Weller SLR 56 97 0 10 May 2021
Concept Bottleneck Models Pang Wei Koh Thao Nguyen Y. S. Tang Stephen Mussmann Emma Pierson Been Kim Percy Liang 101 835 0 09 Jul 2020
Shortcut Learning in Deep Neural Networks Robert Geirhos J. Jacobsen Claudio Michaelis R. Zemel Wieland Brendel Matthias Bethge Felix Wichmann 221 2,061 0 16 Apr 2020
On Completeness-aware Concept-Based Explanations in Deep Neural Networks Chih-Kuan Yeh Been Kim Sercan O. Arik Chun-Liang Li Tomas Pfister Pradeep Ravikumar FAtt 291 307 0 17 Oct 2019
Influence-Directed Explanations for Deep Convolutional Networks Klas Leino S. Sen Anupam Datta Matt Fredrikson Linyi Li TDI FAtt 102 75 0 11 Feb 2018

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.