Efficient rule mining and compression for RDF style KB based on Horn rules.

The volume of published linked open datasets in RDF format is growing exponentially in the last decades. With this continuous proliferation of this growth, demands for managing, accessing, and compressing the RDF dataset have become increasingly important. Most approaches are focused on the structured compression technique while a very few researches have been done for compact representation of the RDF dataset. In this paper, we have proposed an efficient rule mining and compression approach for RDF datasets through various meaningful semantic association rules determined from the RDF graph. We have introduced grammar-based pattern system, clustering of rules, rules pruning, and Top-k scheme to improve the expressiveness of rule patterns, identify the similarity within the random pair of rules, extract the most delicate rules, find the accurate mining threshold, and efficiently learn the rules during the rule mining process from RDF Knowledge Base. Our proposed system uses Horn rules to achieve better compression through storing the triples matched with the precedent part while deleting the triples matched with the head part of the rules. For decreasing the mining time, we have introduced the ranking of the rules. The experimental result on the benchmark dataset asserts that our proposed rule mining and compression scheme has achieved approximately 22.10%, 40.5%, and 44% better compression than the exiting AMIE+, Rule-based compression, and TripleBit approaches, respectively. Our system also has achieved better performance both in terms of compression time and rule mining cost. [ABSTRACT FROM AUTHOR]