Abstract
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.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Kůr, V., Kukučka, A., Brázdil, T., & Musil, V. (2026). A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees. https://omanscience.com/en/articles/a-unifying-framework-of-concept-based-explainable-ai-with-completeness-guarantees
MLA 9
Kůr, Vojtěch, et al. "A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees." https://omanscience.com/en/articles/a-unifying-framework-of-concept-based-explainable-ai-with-completeness-guarantees.
Chicago (author–date)
Kůr, Vojtěch, Adam Kukučka, Tomáš Brázdil, and Vít Musil. 2026. "A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees." https://omanscience.com/en/articles/a-unifying-framework-of-concept-based-explainable-ai-with-completeness-guarantees.
Harvard
Kůr, V., Kukučka, A., Brázdil, T. and Musil, V. (2026) 'A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees', Available at: https://omanscience.com/en/articles/a-unifying-framework-of-concept-based-explainable-ai-with-completeness-guarantees.
Vancouver
Kůr V, Kukučka A, Brázdil T, Musil V. A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees. https://omanscience.com/en/articles/a-unifying-framework-of-concept-based-explainable-ai-with-completeness-guarantees
IEEE
V. Kůr, A. Kukučka, T. Brázdil, and V. Musil, "A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees," https://omanscience.com/en/articles/a-unifying-framework-of-concept-based-explainable-ai-with-completeness-guarantees.