@online{KoutraKangVreekenFaloutsosarXiv2014,
TITLE = {{VoG}: {Summarizing} and Understanding Large Graphs},
AUTHOR = {Koutra, Danai and Kang, U and Vreeken, Jilles and Faloutsos, Christos},
LANGUAGE = {eng},
URL = {http://arxiv.org/abs/1406.3411},
EPRINT = {1406.3411},
EPRINTTYPE = {arXiv},
YEAR = {2014},
ABSTRACT = {How can we succinctly describe a million-node graph with a few simple sentences? How can we measure the "importance" of a set of discovered subgraphs in a large graph? These are exactly the problems we focus on. Our main ideas are to construct a "vocabulary" of subgraph-types that often occur in real graphs (e.g., stars, cliques, chains), and from a set of subgraphs, find the most succinct description of a graph in terms of this vocabulary. We measure success in a well-founded way by means of the Minimum Description Length (MDL) principle: a subgraph is included in the summary if it decreases the total description length of the graph. Our contributions are three-fold: (a) formulation: we provide a principled encoding scheme to choose vocabulary subgraphs; (b) algorithm: we develop \method, an efficient method to minimize the description cost, and (c) applicability: we report experimental results on multi-million-edge real graphs, including Flickr and the Notre Dame web graph.},
}