Non-Parametric Learning of Gaifman Models
This work addresses structure learning in relational models, which is incremental as it builds on existing Gaifman model frameworks.
The paper tackles the problem of structure learning for Gaifman models by proposing a method to learn relational features from knowledge bases, resulting in superior performance over classical rule-learning in empirical evaluations on real datasets.
We consider the problem of structure learning for Gaifman models and learn relational features that can be used to derive feature representations from a knowledge base. These relational features are first-order rules that are then partially grounded and counted over local neighborhoods of a Gaifman model to obtain the feature representations. We propose a method for learning these relational features for a Gaifman model by using relational tree distances. Our empirical evaluation on real data sets demonstrates the superiority of our approach over classical rule-learning.