-
Graphite: Iterative Generative Modeling of Graphs
Graphs are a fundamental abstraction for modeling relational data. Howev...
read it
-
Dynamic Graph Neural Networks
Graphs, which describe pairwise relations between objects, are essential...
read it
-
Small-Variance Asymptotics for Nonparametric Bayesian Overlapping Stochastic Blockmodels
The latent feature relational model (LFRM) is a generative model for gra...
read it
-
Graph Learning Network: A Structure Learning Algorithm
Recently, graph neural networks (GNNs) has proved to be suitable in task...
read it
-
Dirichlet Graph Variational Autoencoder
Graph Neural Networks (GNNs) and Variational Autoencoders (VAEs) have be...
read it
-
Non-Parametric Graph Learning for Bayesian Graph Neural Networks
Graphs are ubiquitous in modelling relational structures. Recent endeavo...
read it
-
Surface Networks
We study data-driven representations for three-dimensional triangle mesh...
read it
Stochastic Blockmodels meet Graph Neural Networks
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 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 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.
READ FULL TEXT
Comments
There are no comments yet.