Theory reconstruction: a representation learning view on predicate invention
This is an incremental proposal to unify predicate invention and theory revision, potentially benefiting researchers in relational and deep learning fields.
The paper tackles the problem of predicate invention by proposing a theory reconstruction approach that extends autoencoder-based representation learning to relational settings, aiming to bridge relational and deep learning communities.
With this positional paper we present a representation learning view on predicate invention. The intention of this proposal is to bridge the relational and deep learning communities on the problem of predicate invention. We propose a theory reconstruction approach, a formalism that extends autoencoder approach to representation learning to the relational settings. Our intention is to start a discussion to define a unifying framework for predicate invention and theory revision.