# NeuralLog: a Neural Logic Language

arXiv: https://arxiv.org/abs/2105.01442 · HTML: https://mlsanity.com/paper/2105.01442/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 4 May 2021.

## Builds on (most cited first, 5 of 5)

- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Neural Logic Machines](https://mlsanity.com/paper/1904.11694/) (2019)
- [TensorLog: Deep Learning Meets Probabilistic DBs](https://mlsanity.com/paper/1707.05390/) (2017)
- [RelNN: A Deep Neural Model for Relational Learning](https://mlsanity.com/paper/1712.02831/) (2017)
- [Neural Networks for Relational Data](https://mlsanity.com/paper/1909.04723/) (2019)

## Built on by (most cited first, 2 of 2)

- [Knowledge Enhanced Neural Networks for relational domains](https://mlsanity.com/paper/2205.15762/) (2022)
- [A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks](https://mlsanity.com/paper/2107.10295/) (2021)

## Abstract (arXiv)

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.