Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning

2024-10-04

arXiv.org

AI Summary

Existing neural-symbolic learning frameworks suffer from poor efficiency on complex reasoning tasks and large-scale datasets. This paper introduces Dolphin, a programmable neural-symbolic learning framework that pioneers a CPU-GPU collaborative execution paradigm: symbolic reasoning—including recursion and black-box function invocation—is performed on the CPU, while probabilistic computation and end-to-end differentiable training are accelerated on the GPU. Dolphin features a Python-based domain-specific language (DSL) frontend, integrating a symbolic execution engine, GPU-accelerated automatic differentiation, and a hybrid hardware scheduling mechanism. Evaluated on 13 cross-modal, high-difficulty benchmarks, Dolphin achieves stable convergence and state-of-the-art accuracy—whereas baseline systems such as Scallop routinely time out. On simpler tasks, Dolphin delivers 1.71×–62× speedups. Overall, Dolphin significantly enhances the scalability, practicality, and deployability of neural-symbolic systems.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

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 that tackles these challenges by supporting neurosymbolic programs in Python, executing complex symbolic reasoning on the CPU while vectorizing probabilistic computations and gradient propagation on the GPU. Across 13 benchmarks spanning tasks over text, image, and video data, with symbolic reasoning features like recursion and black-box functions, Dolphin converges to state-of-the-art accuracies on the more complex benchmarks while existing frameworks such as Scallop, ISED, and IndeCateR+ fail to converge within the time limit. On simpler benchmarks, Dolphin matches their performance, while achieving these results 1.71x to 62x faster than the baselines. Overall, Dolphin advances the scalability of neurosymbolic frameworks, achieving state-of-the-art efficiency and convergence on difficult benchmarks where existing frameworks struggle.

Problem

• Neurosymbolic Learning
• Efficiency
• Large-scale Data

Innovation

• Neuro-Symbolic Learning
• CPU-GPU Integration
• Large-Scale Efficiency