Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908566614441984 |
|---|---|
| author | Biberstein, Paul Li, Ziyang Devietti, Joseph Naik, Mayur |
| author_facet | Biberstein, Paul Li, Ziyang Devietti, Joseph Naik, Mayur |
| contents | Neurosymbolic programs combine deep learning with symbolic reasoning to achieve better data efficiency, interpretability, and generalizability compared to standalone deep learning approaches. However, existing neurosymbolic learning frameworks implement an uneasy marriage between a highly scalable, GPU-accelerated neural component and a slower symbolic component that runs on CPUs.
We propose Lobster, a unified framework for harnessing GPUs in an end-to-end manner for neurosymbolic learning. Lobster maps a general neurosymbolic language based on Datalog to the GPU programming paradigm. This mapping is implemented via compilation to a new intermediate language called APM. The extra abstraction provided by apm allows Lobster to be both flexible, supporting discrete, probabilistic, and differentiable modes of reasoning on GPU hardware with a library of provenance semirings, and performant, implementing new optimization passes.
We demonstrate that Lobster programs can solve interesting problems spanning the domains of natural language processing, image processing, program reasoning, bioinformatics, and planning. On a suite of 9 applications, Lobster achieves an average speedup of 3.9x over Scallop, a state-of-the-art neurosymbolic framework, and enables scaling of neurosymbolic solutions to previously infeasible tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21937 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming Biberstein, Paul Li, Ziyang Devietti, Joseph Naik, Mayur Programming Languages Artificial Intelligence Distributed, Parallel, and Cluster Computing Machine Learning Neurosymbolic programs combine deep learning with symbolic reasoning to achieve better data efficiency, interpretability, and generalizability compared to standalone deep learning approaches. However, existing neurosymbolic learning frameworks implement an uneasy marriage between a highly scalable, GPU-accelerated neural component and a slower symbolic component that runs on CPUs. We propose Lobster, a unified framework for harnessing GPUs in an end-to-end manner for neurosymbolic learning. Lobster maps a general neurosymbolic language based on Datalog to the GPU programming paradigm. This mapping is implemented via compilation to a new intermediate language called APM. The extra abstraction provided by apm allows Lobster to be both flexible, supporting discrete, probabilistic, and differentiable modes of reasoning on GPU hardware with a library of provenance semirings, and performant, implementing new optimization passes. We demonstrate that Lobster programs can solve interesting problems spanning the domains of natural language processing, image processing, program reasoning, bioinformatics, and planning. On a suite of 9 applications, Lobster achieves an average speedup of 3.9x over Scallop, a state-of-the-art neurosymbolic framework, and enables scaling of neurosymbolic solutions to previously infeasible tasks. |
| title | Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming |
| topic | Programming Languages Artificial Intelligence Distributed, Parallel, and Cluster Computing Machine Learning |
| url | https://arxiv.org/abs/2503.21937 |