# Relational Neural Markov Random Fields

arXiv: https://arxiv.org/abs/2110.09647 · HTML: https://mlsanity.com/paper/2110.09647/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 10 of 10)

- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Conditional Random Fields as Recurrent Neural Networks](https://mlsanity.com/paper/1502.03240/) (2015)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Probabilistic Logic Neural Networks for Reasoning](https://mlsanity.com/paper/1906.08495/) (2019)
- [From Statistical Relational to Neuro-Symbolic Artificial Intelligence](https://mlsanity.com/paper/2003.08316/) (2020)
- [Neural Markov Logic Networks](https://mlsanity.com/paper/1905.13462/) (2019)
- [End-to-End Training of Hybrid CNN-CRF Models for Stereo](https://mlsanity.com/paper/1611.10229/) (2016)
- [Deep Markov Random Field for Image Modeling](https://mlsanity.com/paper/1609.02036/) (2016)
- [Expectation Particle Belief Propagation](https://mlsanity.com/paper/1506.05934/) (2015)

## Abstract (arXiv)

Statistical Relational Learning (SRL) models have attracted significant attention due to their ability to model complex data while handling uncertainty. However, most of these models have been limited to discrete domains due to their limited potential functions. We introduce Relational Neural Markov Random Fields (RN-MRFs) which allow for handling of complex relational hybrid domains. The key advantage of our model is that it makes minimal data distributional assumptions and can seamlessly allow for human knowledge through potentials or relational rules. We propose a maximum pseudolikelihood estimation-based learning algorithm with importance sampling for training the neural potential parameters. Our empirical evaluations across diverse domains such as image processing and relational object mapping, clearly demonstrate its effectiveness against non-neural counterparts.