Scallop: A Language for Neurosymbolic Programming
This addresses the problem of integrating logical domain knowledge into machine learning for AI practitioners, offering a more efficient and interpretable approach, though it builds on existing paradigms like Datalog and provenance semirings.
The authors tackled the challenge of combining deep learning and logical reasoning by introducing Scallop, a language for neurosymbolic programming, which achieved comparable or superior accuracy to state-of-the-art models while improving runtime, data efficiency, interpretability, and generalizability across eight applications.
We present Scallop, a language which combines the benefits of deep learning and logical reasoning. Scallop enables users to write a wide range of neurosymbolic applications and train them in a data- and compute-efficient manner. It achieves these goals through three key features: 1) a flexible symbolic representation that is based on the relational data model; 2) a declarative logic programming language that is based on Datalog and supports recursion, aggregation, and negation; and 3) a framework for automatic and efficient differentiable reasoning that is based on the theory of provenance semirings. We evaluate Scallop on a suite of eight neurosymbolic applications from the literature. Our evaluation demonstrates that Scallop is capable of expressing algorithmic reasoning in diverse and challenging AI tasks, provides a succinct interface for machine learning programmers to integrate logical domain knowledge, and yields solutions that are comparable or superior to state-of-the-art models in terms of accuracy. Furthermore, Scallop's solutions outperform these models in aspects such as runtime and data efficiency, interpretability, and generalizability.