一句话：提出 Lobster，将基于 Datalog 的神经符号程序编译到 GPU，实现端到端加速与可扩展推理。
神经符号程序结合深度学习与符号推理，可提升数据效率、可解释性与泛化能力。但现有框架通常将高可扩展的 GPU 神经组件与较慢的 CPU 符号组件割裂结合，难以端到端利用 GPU。Lobster 是一个统一的神经符号学习框架，将基于 Datalog 的通用神经符号语言映射到 GPU 编程范式，并通过编译到新中间语言 APM 实现该映射。APM 的抽象使 Lobster 兼具灵活性，借助 provenance semiring 库支持 GPU 上的离散、概率与可微推理，同时通过新的优化 pass 保证性能。评估覆盖 NLP、图像处理、程序推理、生物信息与规划等 9 个应用；相较 Scallop，Lobster 平均加速 3.9 倍，并可将神经符号方案扩展到此前不可行的任务。
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.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{Biberstein0DN26,
title = {Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming},
author = {Paul Biberstein and Ziyang Li and Joseph Devietti and Mayur Naik},
booktitle = {ASPLOS},
year = {2025},
doi = {10.1145/3760250.3762232}
}