用GPU加速神经符号编程，让推理更快更通用。
Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming
- 将Datalog语言编译为GPU可运行的中间层APM，实现端到端加速。
- 在9个任务上平均快3.9倍，突破原有计算瓶颈。
- 适合需要高效推理的AI研究者与工程落地团队。
神经符号程序结合深度学习与符号推理，相比纯深度学习方法具有更高的数据效率、可解释性和泛化能力。然而，现有框架中神经部分依赖GPU加速，符号部分仍运行在速度较慢的CPU上，难以协同。本文提出Lobster，一个统一的神经符号学习框架，支持在端到端层面利用GPU。Lobster将基于Datalog的通用神经符号语言映射到GPU编程范式，通过编译至一种新型中间语言APM实现。APM提供的额外抽象使Lobster兼具灵活性——支持离散、概率和可微推理模式，配备经过验证的溯源半环库；同时具备高性能，引入新优化策略。实验表明，Lobster能解决自然语言处理、图像处理、程序推理、生物信息学和规划等领域的多个复杂问题。在9个应用任务上，平均速度比当前最先进的Scallop框架快3.9倍，并实现了此前无法完成的规模扩展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。