A Complexity Map of Probabilistic Reasoning for Neurosymbolic Classification Techniques

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ledaguenel, Arthur, Hudelot, Céline, Khouadjia, Mostepha
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913661373644800
author Ledaguenel, Arthur
Hudelot, Céline
Khouadjia, Mostepha
author_facet Ledaguenel, Arthur
Hudelot, Céline
Khouadjia, Mostepha
contents Neurosymbolic artificial intelligence is a growing field of research aiming to combine neural network learning capabilities with the reasoning abilities of symbolic systems. Informed multi-label classification is a sub-field of neurosymbolic AI which studies how to leverage prior knowledge to improve neural classification systems. Recently, a family of neurosymbolic techniques for informed classification based on probabilistic reasoning has gained significant traction. Unfortunately, depending on the language used to represent prior knowledge, solving certain probabilistic reasoning problems can become prohibitively hard when the number of classes increases. Therefore, the asymptotic complexity of probabilistic reasoning is of cardinal importance to assess the scalability of such techniques. In this paper, we develop a unified formalism for four probabilistic reasoning problems. Then, we compile several known and new tractability results into a single complexity map of probabilistic reasoning. We build on top of this complexity map to characterize the domains of scalability of several techniques. We hope this work will help neurosymbolic AI practitioners navigate the scalability landscape of probabilistic neurosymbolic techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2404_08404
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Complexity Map of Probabilistic Reasoning for Neurosymbolic Classification Techniques
Ledaguenel, Arthur
Hudelot, Céline
Khouadjia, Mostepha
Artificial Intelligence
Computational Complexity
Machine Learning
Symbolic Computation
Neurosymbolic artificial intelligence is a growing field of research aiming to combine neural network learning capabilities with the reasoning abilities of symbolic systems. Informed multi-label classification is a sub-field of neurosymbolic AI which studies how to leverage prior knowledge to improve neural classification systems. Recently, a family of neurosymbolic techniques for informed classification based on probabilistic reasoning has gained significant traction. Unfortunately, depending on the language used to represent prior knowledge, solving certain probabilistic reasoning problems can become prohibitively hard when the number of classes increases. Therefore, the asymptotic complexity of probabilistic reasoning is of cardinal importance to assess the scalability of such techniques. In this paper, we develop a unified formalism for four probabilistic reasoning problems. Then, we compile several known and new tractability results into a single complexity map of probabilistic reasoning. We build on top of this complexity map to characterize the domains of scalability of several techniques. We hope this work will help neurosymbolic AI practitioners navigate the scalability landscape of probabilistic neurosymbolic techniques.
title A Complexity Map of Probabilistic Reasoning for Neurosymbolic Classification Techniques
topic Artificial Intelligence
Computational Complexity
Machine Learning
Symbolic Computation
url https://arxiv.org/abs/2404.08404