Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning

TL;DR

DOLPHIN is a scalable neurosymbolic learning framework that efficiently combines symbolic reasoning with deep learning, achieving state-of-the-art accuracy and speed on complex tasks involving text, images, and videos.

Contribution

It introduces a Python-based framework that supports complex symbolic reasoning on CPU and probabilistic computations on GPU, significantly improving scalability and convergence.

Findings

Achieves state-of-the-art accuracy on complex benchmarks

Converges faster than existing frameworks by 1.71x to 62x

Handles symbolic features like recursion and black-box functions effectively

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. The code is published at https://github.com/Dolphin-NeSy/Dolphin.