Embedded Space Analytics

Navy needs a real-time graph embedding tool for analyzing huge graphs (millions of nodes and billions of edges) from diverse sources. However, current approaches cannot provide dynamic and scalable graph analytics to signify the military value of tactical data. In this project, InfoBeyond advocates EStreaming (Embedding & Streaming) for scalable and efficient graph streaming. EStreaming promotes big data streaming technology where unsupervised and semi-supervised machine learning algorithms can be conducted over the streaming platform. It can split a huge graph into small subgraphs such that distributed graph embedding can be conducted in parallel among a set of processors. Meanwhile, the graph embedding can be effectively merged and visualized. Considering the diversity of Navy applications, EStreaming is an open platform that can implement various graph embedding algorithms. Compared to other algorithms, DLINE can be conducted from the internal relations and the similarity among the persons in the solider, enemy, and other social networks. EStreaming has a learning model to integrate supervised, unsupervised, and semi-supervised learning algorithms for analyzing the embedded data. It allows dynamically and continuously tracking nodes/behaviors/events/attacks and capture perishable opportunities for decision making in response to vulnerable graph events. These capabilities are not provided in the traditional approaches.