NeuPSL: Neural Probabilistic Soft Logic

TL;DR

NeuPSL introduces a neuro-symbolic framework that combines symbolic reasoning with neural perception, improving performance and efficiency across multiple tasks through an energy-based modeling approach.

Contribution

It presents Neural Probabilistic Soft Logic (NeuPSL), a novel neuro-symbolic framework that unifies symbolic reasoning with neural perception using energy-based models.

Findings

Achieves up to 30% improvement over neural networks.

Outperforms existing NeSy methods by 10% on MNIST-Addition.

Speeds up citation network task by 40 times.

Abstract

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.