Timezone: »

 
Poster
Edge-exchangeable graphs and sparsity
Diana Cai · Trevor Campbell · Tamara Broderick

Mon Dec 05 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #162
in Monday Posters »

Many popular network models rely on the assumption of (vertex) exchangeability, in which the distribution of the graph is invariant to relabelings of the vertices. However, the Aldous-Hoover theorem guarantees that these graphs are dense or empty with probability one, whereas many real-world graphs are sparse. We present an alternative notion of exchangeability for random graphs, which we call edge exchangeability, in which the distribution of a graph sequence is invariant to the order of the edges. We demonstrate that edge-exchangeable models, unlike models that are traditionally vertex exchangeable, can exhibit sparsity. To do so, we outline a general framework for graph generative models; by contrast to the pioneering work of Caron and Fox (2015), models within our framework are stationary across steps of the graph sequence. In particular, our model grows the graph by instantiating more latent atoms of a single random measure as the dataset size increases, rather than adding new atoms to the measure.

Keywords: Bayesian Nonparametrics

Author Information

Diana Cai (University of Chicago)

I am a PhD student at Princeton University. I work in the area of probabilistic modeling and Bayesian nonparametrics.

Trevor Campbell (MIT)
Tamara Broderick (MIT)

More from the Same Authors