Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming

• URL: http://arxiv.org/abs/2503.21937v1
• Date: Thu, 27 Mar 2025 19:32:58 GMT
• Title: Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming
• Authors: Paul Biberstein, Ziyang Li, Joseph Devietti, Mayur Naik,
• Abstract summary: Neurosymbolic programs combine deep learning with symbolic reasoning to achieve better data efficiency, interpretability, and generalizability.<n>Existing neurosymbolic learning frameworks implement an uneasy marriage between a highly scalable, GPU-accelerated neural component with a slower symbolic component that runs on CPUs.<n>We propose Lobster, a unified framework for harnessing GPU in an end-to-end manner for neurosymbolic learning.
• Score: 10.129565359989044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 with 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 8 applications, Lobster achieves an average speedup of 5.3x over Scallop, a state-of-the-art neurosymbolic framework, and enables scaling of neurosymbolic solutions to previously infeasible tasks.

Related papers

• CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning [9.509171667627491]
  We introduce CTSketch, a novel, scalable neurosymbolic learning algorithm. We show that CTSketch pushes neurosymbolic learning to new scales that have previously been unattainable.
  arXiv  Detail & Related papers  (2025-03-31T14:08:58Z)
• Compositional Generalization Across Distributional Shifts with Sparse Tree Operations [77.5742801509364]
  We introduce a unified neurosymbolic architecture called the Differentiable Tree Machine.<n>We significantly increase the model's efficiency through the use of sparse vector representations of symbolic structures.<n>We enable its application beyond the restricted set of tree2tree problems to the more general class of seq2seq problems.
  arXiv  Detail & Related papers  (2024-12-18T17:20:19Z)
• Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning [17.61843819105099]
  We introduce Dolphin, a framework that supports neurosymbolic programs in Python.<n>Across 13 benchmarks spanning tasks over text, image, and video data, Dolphin converges to state-of-the-art accuracies.
  arXiv  Detail & Related papers  (2024-10-04T12:12:36Z)
• The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning [54.56905063752427]
  Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI systems. Existing pipelines that train the neural and symbolic components sequentially require extensive labelling. New architecture, NeSyGPT, fine-tunes a vision-language foundation model to extract symbolic features from raw data.
  arXiv  Detail & Related papers  (2024-02-02T20:33:14Z)
• Scallop: A Language for Neurosymbolic Programming [14.148819428748597]
  Scallop is a language that combines the benefits of deep learning and logical reasoning. It is capable of expressing algorithmic reasoning in diverse and challenging AI tasks. It provides a succinct interface for machine learning programmers to integrate logical domain knowledge.
  arXiv  Detail & Related papers  (2023-04-10T18:46:53Z)
• SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming [15.814914345000574]
  We introduce SLASH -- a novel deep probabilistic programming language (DPPL) At its core, SLASH consists of Neural-Probabilistic Predicates (NPPs) and logical programs which are united via answer set programming. We evaluate SLASH on the benchmark data of MNIST addition as well as novel tasks for DPPLs such as missing data prediction and set prediction with state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-10-07T12:35:55Z)
• Neuromorphic scaling advantages for energy-efficient random walk computation [0.28144129864580447]
  Neuromorphic computing aims to replicate the brain's computational structure and architecture in man-made hardware. We show that high-degree parallelism and configurability of spiking neuromorphic architectures makes them well-suited to implement random walks via discrete time chains. We find that NMC platforms, at a sufficient scale, can drastically reduce the energy demands of high-performance computing platforms.
  arXiv  Detail & Related papers  (2021-07-27T19:44:33Z)
• High-performance symbolic-numerics via multiple dispatch [52.77024349608834]
  Symbolics.jl is an extendable symbolic system which uses dynamic multiple dispatch to change behavior depending on the domain needs. We show that by formalizing a generic API on actions independent of implementation, we can retroactively add optimized data structures to our system. We demonstrate the ability to swap between classical term-rewriting simplifiers and e-graph-based term-rewriting simplifiers.
  arXiv  Detail & Related papers  (2021-05-09T14:22:43Z)
• GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training [59.160154997555956]
  We present GradInit, an automated and architecture method for initializing neural networks. It is based on a simple agnostic; the variance of each network layer is adjusted so that a single step of SGD or Adam results in the smallest possible loss value. It also enables training the original Post-LN Transformer for machine translation without learning rate warmup.
  arXiv  Detail & Related papers  (2021-02-16T11:45:35Z)
• Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning [134.77207192945053]
  Prior methods learn the neural-symbolic models using reinforcement learning approaches. We introduce the textbfgrammar model as a textitsymbolic prior to bridge neural perception and symbolic reasoning. We propose a novel textbfback-search algorithm which mimics the top-down human-like learning procedure to propagate the error.
  arXiv  Detail & Related papers  (2020-06-11T17:42:49Z)
• MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models [96.1052289276254]
  This work introduces a new MAP-solver, based on the popular Dual Block-Coordinate Ascent principle. Surprisingly, by making a small change to the low-performing solver, we derive the new solver MPLP++ that significantly outperforms all existing solvers by a large margin.
  arXiv  Detail & Related papers  (2020-04-16T16:20:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.