← Back to all news
arXiv Machine Learning By Stephen Marcou, Mateo Espinosa Zarlenga, Sonia Laguna, Moritz Vandenhirtz, Julia E. Vogt, Mateja Jamnik

Residual Stochastic Concept Bottleneck Models

Read the original on arXiv Machine Learning →

Residual Stochastic Concept Bottleneck Models (Res‑SCBMs) extend concept‑based models by jointly modeling known concepts and residual variables using a multivariate Gaussian distribution. The learned covariance captures dependencies between concepts and residuals, enabling test‑time concept interventions to influence statistically dependent residuals through Gaussian conditioning. Experiments on concept‑incomplete benchmarks show that Res‑SCBMs outperform competing baselines while preserving effective concept interventions.

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 Machine Learning.

Related stories

arXiv AI
Oct 9

Towards Reasonable Concept Bottleneck Models

The paper introduces CREAMs, a flexible framework for Concept Bottleneck Models that allows explicit encoding of concept‑concept and concept‑task relationships such as mutual exclusivity, hierarchy, and correlations. CREAMs can optionally use a regularized side‑channel to compensate for incomplete concept sets, maintaining competitive performance while encouraging concept‑grounded predictions. The authors also propose a new metric to assess interpretability when predictions partially rely on the side‑channel, and demonstrate that CREAMs support efficient interventions, avoid concept leakage, and match black‑box performance even with missing concepts.

By Nektarios Kalampalikis, Kavya Gupta, Georgi Vitanov, Isabel Valera
safety
More like this →
arXiv AI
Oct 16

Harmful Partial Interventions and Benign Leakage in Concept-based Models

The paper investigates how interventions on intermediate concepts in concept‑based models can sometimes worsen downstream predictions, a problem termed intervention harm. It shows that the previously proposed leakage‑mitigation objective, which optimises for full‑concept interventions, does not reliably prevent harm when only a subset of concepts is altered. The authors propose a new monotonic intervention objective that penalises increases in task loss during partial interventions, and demonstrate that combining this with the endpoint objective substantially reduces both the frequency and severity of partial‑intervention harm while maintaining overall model performance.

By Gregory Verghese, Christopher J. Soelistyo, Mateo Espinosa Zarlenga, Alessandro Barp, Christopher R. S. Banerji
More like this →