Modeling Graph Node Correlations with Neighbor Mixture Models

Abstract

We propose a new model, the Neighbor Mixture Model (NMM), for modeling node labels in a graph. This model aims to capture correlations between the labels of nodes in a local neighborhood. We carefully design the model so it could be an alternative to a Markov Random Field but with more affordable computations. In particular, drawing samples and evaluating marginal probabilities of single labels can be done in linear time. To scale computations to large graphs, we devise a variational approximation without introducing extra parameters. We further use graph neural networks (GNNs) to parameterize the NMM, which reduces the number of learnable parameters while allowing expressive representation learning. The proposed model can be either fit directly to large observed graphs or used to enable scalable inference that preserves correlations for other distributions such as deep generative graph models. Across a diverse set of node classification, image denoising, and link prediction tasks, we show our proposed NMM advances the state-of-the-art in modeling real-world labeled graphs.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• GMNN: Graph Markov Neural Networks
• REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
• Amortized Inference Regularization
• Neural Enhanced Belief Propagation on Factor Graphs
• Stochastic Blockmodels meet Graph Neural Networks