Relational Neural Markov Random Fields

TL;DR

This paper introduces Relational Neural Markov Random Fields (RN-MRFs), a novel model that combines neural potentials with relational structures to handle complex hybrid domains, integrating human knowledge and demonstrating strong empirical performance.

Contribution

It presents RN-MRFs, the first neural-based SRL model capable of modeling complex relational hybrid data with minimal assumptions and human knowledge integration.

Findings

Effective in image processing tasks

Outperforms non-neural SRL models

Handles complex relational domains

Abstract

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.