High throughput indexing for large-scale semantic web data

Cheng, L.; Kotoulas, S.; Ward, T.; Theodoropoulos, G.

Abstract

Distributed RDF data management systems become increasingly important with the growth of the Semantic Web. Currently, several such systems have been proposed, however, their indexing methods meet performance bottlenecks either on data loading or querying when processing large amounts of data. In this work, we propose a high throughout index to enable rapid analysis of large datasets. We adopt a hybrid structure to combine the loading speed of similar-size based methods with the execution speed of graph-based approaches, using dynamic data repartitioning over query workloads. We introduce the design and detailed implementation of our method. Experimental results show that the proposed index can indeed vastly improve loading speeds while remaining competitive in terms of performance. Therefore, the method could be considered as a good choice for RDF analysis in large-scale distributed scenarios.

Citation

Cheng, L., Kotoulas, S., Ward, T., & Theodoropoulos, G. (2015, April). High throughput indexing for large-scale semantic web data. Presented at 30th Annual ACM Symposium on Applied Computing - SAC '15, Salamanca, Spain

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 30th Annual ACM Symposium on Applied Computing - SAC '15
• Start Date: Apr 13, 2015
• End Date: Apr 17, 2015
• Online Publication Date: Apr 13, 2015
• Publication Date: Apr 13, 2015
• Deposit Date: Apr 21, 2016
• Publicly Available Date: Apr 28, 2016
• Pages: 416-422
• Book Title: Proceedings of the 30th Annual ACM Symposium on Applied Computing 2015 (SAC '15) : Salamanca, Spain, April 13 - 17, 2015.
• DOI: https://doi.org/10.1145/2695664.2695920
• Public URL: https://durham-repository.worktribe.com/output/1150775