Incremental partitioning of massive dynamic graphs and its applications to vertex-centric graph processing systems
MetadataShow full item record
Distributed vertex-centric graph processing systems have acquired significant popularity in recent years for processing massive graphs. The manner in which graph data is partitioned and placed on the computational nodes has considerable impact on the performance of distributed vertex-centric clusters. In this dissertation, we propose a novel model for analyzing the performance of such clusters when different partitioning strategies are applied to the computation of various graph algorithms and also propose various metrics for measuring performance of such clusters. Moreover, in this research we consider partitioning of many real world graph data sets, which are dynamic and can essentially be modeled as Time-Evolving Graphs (TEGs). We propose a unique, continuous and multi-cost sensitive approach for partitioning dynamic graphs. Our approach incorporates novel cost functions that take into account major factors that impact the performance of big graph processing clusters. We also present incremental algorithms to efficaciously handle various types of graph dynamics.
Showing items related by title, author, creator and subject.
Pootheri, Sridar Kuttan (uga, 2000-05)Applying the Tutte decomposition of 2-connected graphs into 3-block trees we provide unique structural characterizations of several classes of 2-connected graphs, including minimally 2-connected graphs, minimally ...
Pootheri, Sridar Kuttan (uga, 2000-05)Applying the Tutte decomposition of 2-connected graphys into 3-block trees, unique structural characterizations of several classes of 2-connected graphs were provided in the PhD dissertation of the author under the title ...
Martin, Jacob Gilmore (uga, 2005-12)Singular value decomposition's usefulness in graph bisection,genetic algorithms, and information retrieval is studied. An infor-mation retrieval theorem about latent semantic indexing (LSI) ispresented in detail. Several ...