Communication Dans Un Congrès Année : 2025

Learning From Interpretation Transitions with Unknowns

Maxime Folschette

Résumé

One major challenge when learning dynamical models from actual time series data consists in tackling partial data. Learning from interpretation transition (LFIT) automatically constructs a model of the dynamics of a system from the observation of its state transitions. In this paper, we extend the LFIT framework to learn from transitions between partial states where some variable values are unknown. By modeling the unknown, we achieve an overestimation of the real system regarding both its dynamics and variables interactions. We show through theoretical results the correctness of our approaches and its effectiveness through an experimental evaluation on benchmarks from biological literature.

Fichier principal
Vignette du fichier
ilp24_LFIT_with_unknowns-1.pdf (511.06 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04634356 , version 1 (03-07-2024)
hal-04634356 , version 2 (11-07-2024)

Licence

Identifiants

Citer

Tony Ribeiro, Maxime Folschette, Morgan Magnin, Kotaro Okazaki, Kuo-Yen Lo, et al.. Learning From Interpretation Transitions with Unknowns. 4th International Joint Conference on Learning & Reasoning, Sep 2024, Nanjing, China. pp.66-85, ⟨10.1007/978-3-032-09087-4_5⟩. ⟨hal-04634356v2⟩
649 Consultations
593 Téléchargements

Altmetric

Partager

  • More