Neurosymbolic Programming in Scallop: Principles and Practice
Foundations and Trends® in Programming Languages · 2024-12-30 · 8 (2) · 118-249
DOI: 10.1561/2500000059 ↗At a glance
Journal article in Foundations and Trends® in Programming Languages, published online on 2024-12-30. Written by Ziyang Li and 3 co-authors. Cited 5 times so far (Crossref); 90 references.
Abstract (original language)
Neurosymbolic programming combines the otherwise complementary worlds of deep learning and symbolic reasoning. It thereby enables more accurate, interpretable, and domain-aware solutions to AI tasks. We introduce Scallop, a general-purpose language and compiler toolchain for developing neurosymbolic applications. A Scallop program specifies a suitable decomposition of an AI task’s computation into separate learning and reasoning modules. Learning modules are built using existing machine learning frameworks and range from custom neural models to foundation models for language, vision, and multi-modal data. Reasoning modules are specified in a declarative logic programming language based on Datalog which supports expressive features such as recursion, aggregation, negation, and probabilistic programming over structured relations. Scallop’s compiler enables to automatically train neurosym- bolic programs in a data- and compute-efficient manner using an end-to-end differentiable reasoning framework. Scallop also supports features useful for building real-world applications such as user-defined data types, and foreign interfaces. We demonstrate programming in Scallop for applications that span the domains of image and video processing, natural language processing, planning, and information retrieval in a variety of learning settings such as supervised learning, reinforcement learning, rule learning, contrastive learning, and in-context learning.
Cite
APA
Li, Z., Huang, J., Liu, J., & Naik, M. (2024). Neurosymbolic Programming in Scallop: Principles and Practice. Foundations and Trends® in Programming Languages, 8(2), 118-249. https://doi.org/10.1561/2500000059
Vancouver
Li Z, Huang J, Liu J, Naik M. Neurosymbolic Programming in Scallop: Principles and Practice. Foundations and Trends® in Programming Languages. 2024;8(2):118-249. doi:10.1561/2500000059
BibTeX
@article{Li2024,
author = {Li, Ziyang and Huang, Jiani and Liu, Jason and Naik, Mayur},
title = {Neurosymbolic Programming in Scallop: Principles and Practice},
journal = {Foundations and Trends® in Programming Languages},
year = {2024},
volume = {8},
number = {2},
pages = {118--249},
doi = {10.1561/2500000059}
}
EUVIMED