Relational Neural Markov Random Fields
This addresses the problem of modeling uncertainty in complex relational hybrid domains for researchers in statistical relational learning, though it appears incremental as an extension of existing methods.
The paper tackles the limitation of Statistical Relational Learning models to discrete domains by introducing Relational Neural Markov Random Fields (RN-MRFs), which handle complex relational hybrid domains with minimal distributional assumptions and allow integration of human knowledge. Empirical evaluations in domains like image processing and relational object mapping demonstrate its effectiveness against non-neural counterparts.
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.