Metraipolis › archive › dc_57113efddf4b
Residual Stochastic Concept Bottleneck Models — arXiv:2610.23421
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.23421
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:10:15.897Z
- SHA-256 of the archived text
54b1f95bcabe0a38849e970062032a43072ff76c3b3ab18e7b5432cf3eb5fe11- Stable URL of this page
https://metraipolis.com/documento/dc_57113efddf4b
How to cite
Residual Stochastic Concept Bottleneck Models — arXiv:2610.23421 — arXiv (en), https://arxiv.org/abs/2610.23421 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57113efddf4b (Metraipolis archive dc_57113efddf4b, sha256 54b1f95bcabe0a38849e970062032a43072ff76c3b3ab18e7b5432cf3eb5fe11)
BibTeX
@misc{dc57113efddf4b,
title = {Residual Stochastic Concept Bottleneck Models — arXiv:2610.23421},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.23421},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57113efddf4b; sha256 54b1f95bcabe0a38849e970062032a43072ff76c3b3ab18e7b5432cf3eb5fe11},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23421. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Concept-based models (CMs) learn human-interpretable intermediate representations that enable users to understand the model's reasoning and steer its predictions through test-time concept interventions. However, in realistic settings, their performance can be limited by concept incompleteness, where the training concepts fail to capture all task-relevant information. Adding an unconstrained residual pathway to the model's predictive process can overcome the consequences of incompleteness. However, this introduces an inscrutable, leak-prone prediction pathway that may weaken concept interventions, as these often leave residual variables unchanged. To address this limitation, we introduce Residual Stochastic Concept Bottleneck Models (Res-SCBMs), a family of concept-based models that jointly model concept and residual variables through a multivariate Gaussian distribution. Res-SCBMs learn a covariance structure that explicitly captures dependencies between the known concepts and learnt residual variables, allowing interventions to propagate to statistically dependent residual variables through Gaussian conditioning. This extends the intervention capabilities of previous CMs without requiring concept completeness during training. Our results show that, across multiple concept-incomplete benchmarks, Res-SCBMs improve predictive performance over competing baselines while retaining effective test-time concept interventions. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.23421 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:06:29.548Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).