DeepStochLog: Neural Stochastic Logic Programming
DeepStochLog: Neural Stochastic Logic Programming
复制标题
DeepStochLog：神经随机逻辑编程
DOI：
10.1609/aaai.v36i9.21248
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
L. D. Raedt
中科院分区：
文献类型：
--
作者：
Thomas Winters;G. Marra;Robin Manhaeve;L. D. Raedt
神经符号学习的最新进展（例如 DeepProbLog）用神经谓词扩展了概率逻辑程序。与图形模型一样，这些概率逻辑程序定义了可能世界的概率分布，而推理在计算上是困难的。我们提出了 DeepStochLog，一种基于随机定子句语法（一种随机逻辑程序）的替代神经符号框架。更具体地说，我们将神经语法规则引入随机定语从句语法中，以创建一个可以端到端训练的框架。我们表明，神经随机逻辑编程中的推理和学习规模比神经概率逻辑程序要好得多。此外，实验评估表明 DeepStochLog 在具有挑战性的神经符号学习任务上取得了最先进的结果。
Recent advances in neural-symbolic learning, such as DeepProbLog, extend probabilistic logic programs with neural predicates. Like graphical models, these probabilistic logic programs define a probability distribution over possible worlds, for which inference is computationally hard. We propose DeepStochLog, an alternative neural-symbolic framework based on stochastic definite clause grammars, a kind of stochastic logic program. More specifically, we introduce neural grammar rules into stochastic definite clause grammars to create a framework that can be trained end-to-end. We show that inference and learning in neural stochastic logic programming scale much better than for neural probabilistic logic programs. Furthermore, the experimental evaluation shows that DeepStochLog achieves state-of-the-art results on challenging neural-symbolic learning tasks.