LogicCBMs: Logic-Enhanced Concept-Based Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Vemuri, Deepika SN, Bellamkonda, Gautham, Pola, Aditya, Balasubramanian, Vineeth N
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911307967496192
author Vemuri, Deepika SN
Bellamkonda, Gautham
Pola, Aditya
Balasubramanian, Vineeth N
author_facet Vemuri, Deepika SN
Bellamkonda, Gautham
Pola, Aditya
Balasubramanian, Vineeth N
contents Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring predictions as a linear combination of semantic concepts. However, a linear combination is inherently limiting. So we propose the enhancement of concept-based learning models through propositional logic. We introduce a logic module that is carefully designed to connect the learned concepts from CBMs through differentiable logic operations, such that our proposed LogicCBM can go beyond simple weighted combinations of concepts to leverage various logical operations to yield the final predictions, while maintaining end-to-end learnability. Composing concepts using a set of logic operators enables the model to capture inter-concept relations, while simultaneously improving the expressivity of the model in terms of logic operations. Our empirical studies on well-known benchmarks and synthetic datasets demonstrate that these models have better accuracy, perform effective interventions and are highly interpretable.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07383
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LogicCBMs: Logic-Enhanced Concept-Based Learning
Vemuri, Deepika SN
Bellamkonda, Gautham
Pola, Aditya
Balasubramanian, Vineeth N
Computer Vision and Pattern Recognition
Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring predictions as a linear combination of semantic concepts. However, a linear combination is inherently limiting. So we propose the enhancement of concept-based learning models through propositional logic. We introduce a logic module that is carefully designed to connect the learned concepts from CBMs through differentiable logic operations, such that our proposed LogicCBM can go beyond simple weighted combinations of concepts to leverage various logical operations to yield the final predictions, while maintaining end-to-end learnability. Composing concepts using a set of logic operators enables the model to capture inter-concept relations, while simultaneously improving the expressivity of the model in terms of logic operations. Our empirical studies on well-known benchmarks and synthetic datasets demonstrate that these models have better accuracy, perform effective interventions and are highly interpretable.
title LogicCBMs: Logic-Enhanced Concept-Based Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.07383