NeuralLog: a Neural Logic Language

Victor Guimarães, Vitor Santos Costa

Keywords: Deep learning, logic programming, neural network, relational learning

Abstract: 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.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: A system that compiles first-order logic programs into neural networks.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2105.01442/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=FO5-XDmI4