Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$
Moose improves over propositional-NeSy, fuzzy-logic, and ontology embedding baselines, and presents the first reasoning-shortcut analysis in an OWL EL setting.
We have 3 of 19 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Moose improves over propositional-NeSy, fuzzy-logic, and ontology embedding baselines, and presents the first reasoning-shortcut analysis in an OWL EL setting.
A framework from scratch is developed for NeSy systems, a conservativity theorem is proved that recovers the classical functional when symmetries are trivial, and it is shown that the symmetry the framework exposes is exactly the one behind reasoning shortcuts.
Baobab is presented, which is to the authors' knowledge the first to characterize and mitigate reasoning shortcuts in a non-Horn description logic and machine-checked in Lean 4.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.