Graphs & networks: computing and analytics at lincoln laboratory

Abstract

Over the last decade, Lincoln Laboratory has been conducting research and development in graph and network analytics, and the computing architectures that support these analytics as data sets scale to million-node graphs and beyond. This talk gives a brief introduction to the application domains that can exploit graph analytics, and the "big data" computational challenges inherent in these applications. The talk then presents a computational framework for graph and network analytics based on spectral analysis methods. To support the programming and computational needs of large scale graphs and complex analytics, Lincoln Laboratory has also been developing specialized programming languages and computing architectures. Recent advances in these areas and future directions are discussed.