Scallop: A Language for Neurosymbolic Programming

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 symbo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of ACM on programming languages Ročník 7; číslo PLDI; s. 1463 - 1487
Hlavní autoři: Li, Ziyang, Huang, Jiani, Naik, Mayur
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York, NY, USA ACM 06.06.2023
Témata:
Computing methodologies
Domain specific languages
Learning paradigms
Logical and relational learning
Probabilistic reasoning
Software and its engineering
Differentiable reasoning
Neurosymbolic methods
ISSN:2475-1421, 2475-1421
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:2475-1421
2475-1421
DOI:10.1145/3591280