NeuralLog: a Neural Logic Language
This work addresses the need for combining logic and neural networks in machine learning, offering a novel approach for domains with numeric attributes, though it appears incremental in bridging existing fields.
The authors tackled the problem of integrating logic programming with deep learning for domains with real-valued attributes by proposing NeuralLog, a first-order logic language compiled to neural networks, which achieved better ROC curve results in four datasets for link prediction and classification tasks compared to existing systems.
Application domains that require considering relationships among objects which have real-valued attributes are becoming even more important. In this paper we propose NeuralLog, a first-order logic language that is compiled to a neural network. The main goal of NeuralLog is to bridge logic programming and deep learning, allowing advances in both fields to be combined in order to obtain better machine learning models. The main advantages of NeuralLog are: to allow neural networks to be defined as logic programs; and to be able to handle numeric attributes and functions. We compared NeuralLog with two distinct systems that use first-order logic to build neural networks. We have also shown that NeuralLog can learn link prediction and classification tasks, using the same theory as the compared systems, achieving better results for the area under the ROC curve in four datasets: Cora and UWCSE for link prediction; and Yelp and PAKDD15 for classification; and comparable results for link prediction in the WordNet dataset.