Mariano Consens - Introduction to Graph-Parallel Analytics Systems

This talk provides an introduction to Graph-Parallel Analytics Systems - scalable computing platforms that have evolved from the initially supported map-reduce paradigm to support an iterative, node-centric, parallel processing model.
We start by motivating a representative graph problem - computing bisimilar contractions. We cover the classic naïve algorithm that has been parallelized in message passing environments and adapted to provide map reduce solutions. We then describe an implementation on a multi-core graph-parallel processing framework, and introduce a novel optimization that takes advantage of the capabilities available in Graph-Parallel Analytics Systems. We conclude with a comparison and discussion of the experimental results.

Bio:
Mariano Consens research interests are in the areas of Data Management and the Web, with a focus on linked data, graph data, analytics for semistructured data, privacy, XML searching, and autonomic systems. He has over 70 publications, including journal publications selected from best conference papers and several patents. Mariano received his PhD and MSc degrees in Computer Science from the University of Toronto, and a Computer Systems Engineer degree from the Universidad de la Republica, Uruguay. Consens is a University of Toronto faculty member and a Visiting Scientist at the IBM Center for Advanced Studies in Toronto. In addition, he has been active in the software industry as a founder and CTO of a couple of software startups, as well as a Visiting Scientist at Yahoo! Research.