Declarative Design of Neural Predicates in Neuro-Symbolic Systems
This addresses a core limitation in neuro-symbolic AI systems, making them more flexible and efficient for reasoning tasks.
The authors tackled the lack of declarativeness in neuro-symbolic systems by proposing a framework for fully declarative neural predicates, which preserves learning and reasoning capabilities and enables answering arbitrary queries after training on a single query type.
Neuro-symbolic systems (NeSy), which claim to combine the best of both learning and reasoning capabilities of artificial intelligence, are missing a core property of reasoning systems: Declarativeness. The lack of declarativeness is caused by the functional nature of neural predicates inherited from neural networks. We propose and implement a general framework for fully declarative neural predicates, which hence extends to fully declarative NeSy frameworks. We first show that the declarative extension preserves the learning and reasoning capabilities while being able to answer arbitrary queries while only being trained on a single query type.