← Back to all news
arXiv Statistics ML By Julia Wenkmann, Damien Garreau

On The Variability of Concept Activation Vectors

Read the original on arXiv Statistics ML →

The paper investigates how Concept Activation Vectors (CAVs), used for concept‑based explanations in AI, vary due to the randomness in sampling training examples. A theoretical analysis shows that the variance of CAVs decreases roughly as 1/N, where N is the number of sampled examples. Experiments across four modalities confirm this relationship, leading to practical guidelines for efficiently applying CAVs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

Related stories

arXiv Machine Learning
Oct 8

For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature Importance

The paper introduces Ra‑NEM, a method that optimizes the area under insertion and deletion curves to improve the faithfulness of feature importance attributions in machine learning models. By deriving an objective function from faithfulness and approximating its gradient, the authors link insertion curves to top‑k feature selection, enabling a loss function that measures attribution quality. Ra‑NEM, integrated with the neural explanation mask framework, works with any differentiable model, yielding accurate, robust, and fast attributions that outperform existing algorithms on multiple XAI metrics.

By Bj{\o}rn Leth M{\o}ller, Bulat Ibragimov, Christian Igel
efficiency
More like this →
arXiv AI
Oct 16

ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on

The paper introduces ICON decomposition, a method for auditing neural networks by decomposing the variance of intermediate representations into contributions from Independent Canonical Concepts (ICON). Unlike traditional decodability metrics, ICON isolates each concept’s influence while conditioning on all other concepts and the outcome, providing a clearer view of which concepts truly drive predictions. Experiments on simulated data and real-world skin‑cancer and neuroimaging tasks show ICON outperforms seven baseline methods and successfully distinguishes genuine shortcuts from merely correlated features.

By Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter
More like this →