神经符号扩散模型

Neurosymbolic Diffusion Models

May 19, 2025

作者: Emile van Krieken, Pasquale Minervini, Edoardo Ponti, Antonio Vergari

cs.AI

摘要

神经符号（NeSy）预测器通过结合神经感知与符号推理来解决诸如视觉推理等任务。然而，标准的NeSy预测器假设其提取的符号之间条件独立，这限制了它们建模交互和不确定性的能力，常常导致预测过于自信以及分布外泛化性能不佳。为了克服独立性假设的局限，我们引入了神经符号扩散模型（NeSyDMs），这是一类新的NeSy预测器，利用离散扩散来建模符号间的依赖关系。我们的方法在扩散过程的每一步复用NeSy预测器的独立性假设，从而在捕捉符号依赖关系和不确定性量化的同时，实现了可扩展的学习。在包括高维视觉路径规划和基于规则的自动驾驶在内的合成与真实世界基准测试中，NeSyDMs在NeSy预测器中达到了最先进的准确率，并展现出良好的校准性能。

English

Neurosymbolic (NeSy) predictors combine neural perception with symbolic reasoning to solve tasks like visual reasoning. However, standard NeSy predictors assume conditional independence between the symbols they extract, thus limiting their ability to model interactions and uncertainty - often leading to overconfident predictions and poor out-of-distribution generalisation. To overcome the limitations of the independence assumption, we introduce neurosymbolic diffusion models (NeSyDMs), a new class of NeSy predictors that use discrete diffusion to model dependencies between symbols. Our approach reuses the independence assumption from NeSy predictors at each step of the diffusion process, enabling scalable learning while capturing symbol dependencies and uncertainty quantification. Across both synthetic and real-world benchmarks - including high-dimensional visual path planning and rule-based autonomous driving - NeSyDMs achieve state-of-the-art accuracy among NeSy predictors and demonstrate strong calibration.