Subgraph nomination: query by example subgraph retrieval in networks

This paper introduces the subgraph nomination inference task, in which example subgraphs of interest are used to query a network for similarly interesting subgraphs. type problem appears time and again real world problems connected to, example, user recommendation systems structural retrieval tasks social biological/connectomic networks. We formally define framework with an emphasis on notion user-in-the-loop pipeline. In this setting, can provide additional post-nomination light supervision that be incorporated into task. After introducing formalizing we examine nuanced effect user-supervision have performance, both analytically across simulated data examples.