Metraipolis › archive › dc_268eeea2c7aa

CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals — arXiv:2609.37786

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37786
License (as archived): CC0-1.0
Archived: 2026-10-07T18:41:29.875Z
SHA-256 of the archived text: 2244e04464a2f864448efa28f7b95608985b8eea7c817c64160e6c0396740790
Stable URL of this page: https://metraipolis.com/documento/dc_268eeea2c7aa

How to cite

CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals — arXiv:2609.37786 — arXiv (en), https://arxiv.org/abs/2609.37786 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_268eeea2c7aa (Metraipolis archive dc_268eeea2c7aa, sha256 2244e04464a2f864448efa28f7b95608985b8eea7c817c64160e6c0396740790)

BibTeX

@misc{dc268eeea2c7aa,
  title = {CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals — arXiv:2609.37786},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37786},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_268eeea2c7aa; sha256 2244e04464a2f864448efa28f7b95608985b8eea7c817c64160e6c0396740790},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37786. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Concept Bottleneck Models (CBMs) built on vision-language models such as CLIP represent a latent space as human-understandable concepts. These representations are unfaithful: related concepts are entangled, so individual scores do not reflect their intended meaning. We propose CHOQOLATE, an interpretable-by-design layer based on 2-additive Choquet integrals, which merges correlated concepts into compact nodes. Across four datasets, CHOQOLATE achieves a favorable accuracy-interpretability trade-off, with weight-sparse and semantically coherent nodes. A closed-form gradient derivation, backed by experiments, explains why Choquet layers drive this organization without explicit supervision. Choquet weights also map directly to Shapley values, which enables test-time intervention. On standard bias-mitigation benchmarks, suppressing spurious concepts after training performs on par with methods that require group annotations or retraining, while needing neither.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37786 — 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 2026-10-07T18:04:24.907Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).