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 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Logical ReasoningNegationSimilar Papers 제목 키워드 기반
Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming
Neurosymbolic programs combine deep learning with symbolic reasoning to achieve better data efficiency, interpretability, and generalizability compared to standalone deep learning approaches. However, existing neurosymbo…
GPUDolphin: A Programmable Framework for Scalable Neurosymbolic Learning
Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce Dolphin, a framework…
CPUDeep LearningGPUScallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning
Deep learning and symbolic reasoning are complementary techniques for an intelligent system. However, principled combinations of these techniques have limited scalability, rendering them ill-suited for real-world applica…
Logical ReasoningQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)On Improving Neurosymbolic Learning by Exploiting the Representation Space
We study the problem of learning neural classifiers in a neurosymbolic setting where the hidden gold labels of input instances must satisfy a logical formula. Learning in this setting proceeds by first computing (a subse…
On the Promise for Assurance of Differentiable Neurosymbolic Reasoning Paradigms
To create usable and deployable Artificial Intelligence (AI) systems, there requires a level of assurance in performance under many different conditions. Many times, deployed machine learning systems will require more cl…
Adversarial Robustness