timgutberlet/Which-Rules-Entail-This-Fact

This research project is focused on creating an efficient solution for identifying rules which entail certain target facts given a set of rules and a knowledge graph using relational database technologies.

Which Rules Entail this Fact?
An Efficient Approach Using RDBMSs

Tim Gutberlet (tim.gutberlet@students.uni-mannheim.de) & Janik Sauerbier (janik.sauerbier@students.uni-mannheim.de)

Based on this work a paper was published at BTW-2023 (https://dl.gi.de/handle/20.500.12116/40386)

Summary

In this work, we focus on the problem of identifying all rules that entail a certain target fact given a knowledge graph and a set of previously learned rules. This problem is relevant in the context of link prediction and explainability. We propose an efficient approach using relational database technology including indexing, filtering and pre-computing methods. Our experiments demonstrate the efficiency of our approach and the effect of various optimizations on different datasets like YAGO3-10, WN18RR and FB15k-237 using rules learned by the bottom up rule learner AnyBURL.

Folder structure

Code

This folder contains the codebase for relevant software (e.g., AnyBURL) as well as experimental scripts and databases created throughout our project.

Meeting Notes

This folder contains all Meeting Notes including the aganda and resulting ToDo's within the context of the project.

Paper

The final paper, first drafts and LaTeX files.