论文标题
NEUPSL：神经概率软逻辑
NeuPSL: Neural Probabilistic Soft Logic
论文作者
论文摘要
在本文中，我们介绍了一种新型的神经符号（NESY）框架，引入了神经概率软逻辑（NEUPSL），该框架将最新的象征性推理与深层神经网络的低级感知统一。为了建模神经和符号表示之间的边界，我们提出了一个基于能量的模型，基于NESY Energy的模型，并表明它们足够一般，可以包括NEUPSL和许多其他NESY方法。使用此框架，我们展示了如何无缝整合NEUPSL中的神经和符号参数学习和推断。通过广泛的经验评估，我们证明了使用NESY方法的好处，比独立的神经网络模型取得了30％的改善。在一项良好的NESY任务中，NEUPSL通过在低DATA环境中超过现有的NESY方法高达10％，从而展示了其联合推理能力。此外，NEUPSL在规范引用网络任务中的最新方法中的性能提高了5％，最大加快了40倍。
In this paper, we introduce Neural Probabilistic Soft Logic (NeuPSL), a novel neuro-symbolic (NeSy) framework that unites state-of-the-art symbolic reasoning with the low-level perception of deep neural networks. To model the boundary between neural and symbolic representations, we propose a family of energy-based models, NeSy Energy-Based Models, and show that they are general enough to include NeuPSL and many other NeSy approaches. Using this framework, we show how to seamlessly integrate neural and symbolic parameter learning and inference in NeuPSL. Through an extensive empirical evaluation, we demonstrate the benefits of using NeSy methods, achieving upwards of 30% improvement over independent neural network models. On a well-established NeSy task, MNIST-Addition, NeuPSL demonstrates its joint reasoning capabilities by outperforming existing NeSy approaches by up to 10% in low-data settings. Furthermore, NeuPSL achieves a 5% boost in performance over state-of-the-art NeSy methods in a canonical citation network task with up to a 40 times speed up.
