Bernoulli Embeddings for Graphs

Consider users -- perhaps from the research, intelligence, or recruiting community -- who seek to explore graphical data -- perhaps knowledge graphs or social networks. If the graph is small, it is reasonable for these users to directly explore the data by examining nodes and traversing edges. For larger graphs, or for graphs with noisy edges, it rapidly becomes necessary to algorithmically aid users. The problems that arise in this setting are essentially those of information retrieval and recommendation for graphical data, and are well studied [Hasan and Zaki2011, Blanco et al.2013]: identifying the most important edges, predicting links that do not exist, and the like. The responsiveness of these retrieval systems is critical [Gray and Boehm-Davis2000], and has driven numerous system designs in both hardware [Hong et al.2011] and software [Low et al.2014].