Metraipolis › archive › dc_6581f27fafcf
A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees — arXiv:2609.34750
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34750
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:55.122Z
- SHA-256 of the archived text
8279c57066a9fad305dd6a11d085dfbe78422378850fd24575da21f8a337b14c- Stable URL of this page
https://metraipolis.com/documento/dc_6581f27fafcf
How to cite
A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees — arXiv:2609.34750 — arXiv (en), https://arxiv.org/abs/2609.34750 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6581f27fafcf (Metraipolis archive dc_6581f27fafcf, sha256 8279c57066a9fad305dd6a11d085dfbe78422378850fd24575da21f8a337b14c)
BibTeX
@misc{dc6581f27fafcf,
title = {A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees — arXiv:2609.34750},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34750},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6581f27fafcf; sha256 8279c57066a9fad305dd6a11d085dfbe78422378850fd24575da21f8a337b14c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34750. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Concept-based explanations describe neural network predictions through human-understandable properties of inputs called concepts. The field encompasses approaches that differ in how they define and represent concepts and connect them to model predictions. We introduce a theoretical framework that describes these approaches in a common mathematical language and supports a shared analysis of their properties. For concept discovery, which identifies concepts automatically within a latent space of a trained model, we employ a concept autoencoder view. An encoder extracts concept representations from the model's latent space, and a decoder uses them to reconstruct the original latent representation. The autoencoder's reconstruction error measures how accurately its decoder recovers the original latent representation. We revisit model completeness: how well the concepts can reproduce the model's outputs. We show that model incompleteness of the concepts can be bounded by the autoencoder's reconstruction error. The autoencoder view also provides a common way to define individual concept attributions, which measure each concept's contribution to a prediction. We establish when these attributions sum to the model's prediction, and bound the discrepancy otherwise, thus providing attribution completeness guarantees. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.34750 — 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 2026-10-07T20:29:03.150Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).