English

Neural-Symbolic Integration: A Compositional Perspective

Artificial Intelligence 2020-10-23 v1 Machine Learning

Abstract

Despite significant progress in the development of neural-symbolic frameworks, the question of how to integrate a neural and a symbolic system in a \emph{compositional} manner remains open. Our work seeks to fill this gap by treating these two systems as black boxes to be integrated as modules into a single architecture, without making assumptions on their internal structure and semantics. Instead, we expect only that each module exposes certain methods for accessing the functions that the module implements: the symbolic module exposes a deduction method for computing the function's output on a given input, and an abduction method for computing the function's inputs for a given output; the neural module exposes a deduction method for computing the function's output on a given input, and an induction method for updating the function given input-output training instances. We are, then, able to show that a symbolic module -- with any choice for syntax and semantics, as long as the deduction and abduction methods are exposed -- can be cleanly integrated with a neural module, and facilitate the latter's efficient training, achieving empirical performance that exceeds that of previous work.

Keywords

Cite

@article{arxiv.2010.11926,
  title  = {Neural-Symbolic Integration: A Compositional Perspective},
  author = {Efthymia Tsamoura and Loizos Michael},
  journal= {arXiv preprint arXiv:2010.11926},
  year   = {2020}
}
R2 v1 2026-06-23T19:34:00.955Z