We present two algorithms, each depending on a different data fragmentation of the XML tree. They both compute XPath queries in MapReduce, by first computing subqueries and then combining their results. We compute the replication rate of each algorithm and show it is less than 2.
Bibtex: Afrati et al. (2015)
Foto N Afrati, Matthew Damigos, and Manolis Gergatsoulis. Lower bounds on the communication of xpath queries in mapreduce. In EDBT/ICDT Workshops, 38–41. 2015. ↩