SiNA: A Scalable Iterative Network Aligner

Abstract

Given two graphs, network alignment asks for a potentially partial mapping between the vertices of the two graphs. This arises in many applications where data from different sources need to be integrated. Recent graph aligners use the global structure of input graphs and additional information given for the edges and vertices. We present SINA, an efficient, shared memory parallel implementation of such an aligner. Our experimental evaluations on a 32-core shared memory machine showed that SINA scales well for aligning large real-world graphs: SINA can achieve up to 28.5× speedup, and can reduce the total execution time of a graph alignment problem with 2M vertices and 100M edges from 4.5 hours to under 10 minutes. To the best of our knowledge, SINA is the first parallel aligner that uses global structure and vertex and edge attributes to handle large graphs.

Programming Strategies for Irregular Algorithms on the Emu Chick

“…As expected, this improvement increases with the graph size. This improvement in a x86 architecture is reported as 10% in [69]. Second, we see that the PAIR computation scheme enjoys improvements with both vertex layouts, because it has a finer grained task parallelism and hence better workload distribution.…”

“…require accessing different portions of the graph simultaneously. In [69] authors provide parallelization strategies for different stages of gsaNA. However, because of the differences in the architecture and the parallelization framework, the earlier techniques cannot be applied to EMU Chick in a straightforward manner.…”

“…All of these methods have scalability issues. gsaNa [68,69] leverages global graph structure and reduces the problem space and exploits the semantic information to alleviate most of the scalability issues. In addition to these sequential algorithms, we are aware of two parallel approaches for global graph alignment.…”

“…While these parallel algorithms show an important improvement over the state of the art sequential algorithms, the graphs used in the experiments are small in size and there is a high structural similarity. To the best of our knowledge, the use of gsaNA in [69] and in this paper presents the first method for parallel alignment of labeled graphs.…”