AnyBurl rule pruning improves link prediction efficiency under limits
Post-Pruning vs. Early Stopping: Which Works Better for Link Prediction with AnyBurl?
Logic in Computer Science
Summary
Sometimes, computers try to guess missing connections in knowledge graphs using rules. The authors looked at AnyBurl, a tool that finds many such rules but can slow down when there are too many. They studied whether it’s better to stop the rule-finding early or to find many rules and then cut down the list. Their work helps understand how to make predictions faster without losing accuracy.
What this means in practice
- •For knowledge graph engineers: Improve query response times by choosing the best rule management strategy for link prediction tools like AnyBurl under hardware limits.
- •For recommendation system developers: Optimize rule-based inference step to maintain recommendation quality while reducing computational overhead in resource-constrained environments.
Authors
Thomas Eiter, Davide Soldà, Hai Xia
Abstract
Rule-based link prediction combines symbolic and statistical artificial intelligence methods by inductively learning a set of rules from a knowledge graph (KG), with the aim of completing the graph when a query cannot be answered from the KG alone. Several systems have been proposed, and while they perform well on classical benchmarks, even compared with embedding-based systems, many of them produce a large number of rules. This compromises scalability in the query-answering phase, especially under strong hardware constraints. In this work, we investigate the behavior of AnyBurl, a state-of-the-art rule learner for link prediction, to determine whether running it for a given time and then pruning the learned rules yields better query-answering performance at test time than a simpler approach that stops rule generation earlier.