Timezone: »

 
Poster
Stochastic Blockmodels meet Graph Neural Networks
Nikhil Mehta · Lawrence Carin · Piyush Rai

Wed Jun 12 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #180
in Posters Wed »
Stochastic blockmodels (SBM) and their variants, $e.g.$, mixed-membership and overlapping stochastic blockmodels, are latent variable based generative models for graphs. They have proven to be successful for various tasks, such as discovering the community structure and link prediction on graph-structured data. Recently, graph neural networks, $e.g.$, graph convolutional networks, have also emerged as a promising approach to learn powerful representations (embeddings) for the nodes in the graph, by exploiting graph properties such as locality and invariance. In this work, we unify these two directions by developing a \emph{sparse} variational autoencoder for graphs, that retains the interpretability of SBMs, while also enjoying the excellent predictive performance of graph neural nets. Moreover, our framework is accompanied by a fast recognition model that enables fast inference of the node embeddings (which are of independent interest for inference in SBM and its variants). Although we develop this framework for a particular type of SBM, namely the \emph{overlapping} stochastic blockmodel, the proposed framework can be adapted readily for other types of SBMs. Experimental results on several benchmarks demonstrate encouraging results on link prediction while learning an interpretable latent structure that can be used for community discovery.
Keywords: Bayesian Nonparametrics · Clustering · Interpretability · Networks and Relational Learning · Representation Learning

Author Information

Nikhil Mehta (Duke University)
Lawrence Carin (Duke)
Piyush Rai (IIT Kanpur)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors