Thesis Type: Postgraduate
Institution Of The Thesis: Orta Doğu Teknik Üniversitesi, Faculty of Engineering, Department of Computer Engineering, Turkey
Approval Date: 2016
Student: MERVE ASİLER
Consultant: ADNAN YAZICIAbstract:
With the emergence of the big data concept, the big graph database model has become very popular since it provides very flexible and quick querying for the cases that require costly join operations in RDBMs. However, it is a big challenge to find all exact matches of a query graph in a big database graph, which is known as the subgraph isomorphism problem. Although many related studies exist in literature, there is not a perfect algorithm that works for all types of queries efficiently since it is an NP-hard problem. The current subgraph isomorphism approaches built on Ullmann’s idea focus on the strategy of pruning out the irrelevant candidates. Nevertheless, for some databases and queries, their pruning techniques are inadequate. Therefore, they result in poor performance. Moreover, some of those algorithms need large indices that cause extra memory consumption. Motivated by these, we introduce a new subgraph isomorphism algorithm, namely BB-Graph, for querying big database graphs in an efficient manner without requiring large data structures. We test and compare our algorithm with the existing ones, GraphQL and Cypher of Neo4j, on some very big graph database applications and show that our algorithm performs better for most of the query types.