Neural-Symbolic Integration: A Compositional Perspective
This addresses a foundational challenge in neural-symbolic AI for researchers and practitioners, offering a novel integration approach that is incremental in building on existing frameworks.
The paper tackles the problem of integrating neural and symbolic systems in a compositional manner by treating them as black-box modules with exposed methods, enabling clean integration and efficient training. It achieves empirical performance that exceeds previous work, though specific numbers are not provided.
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.