Modeling Graph Node Correlations with Neighbor Mixture Models

03/29/2021
by   Linfeng Liu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2020

Revisiting graph neural networks and distance encoding in a practical view

Graph neural networks (GNNs) are widely used in the applications based o...
research
04/20/2023

Improving Graph Neural Networks on Multi-node Tasks with Labeling Tricks

In this paper, we provide a theory of using graph neural networks (GNNs)...
research
03/28/2018

Graphite: Iterative Generative Modeling of Graphs

Graphs are a fundamental abstraction for modeling relational data. Howev...
research
12/05/2020

Graph Mixture Density Networks

We introduce the Graph Mixture Density Network, a new family of machine ...
research
03/01/2021

CogDL: An Extensive Toolkit for Deep Learning on Graphs

Graph representation learning aims to learn low-dimensional node embeddi...
research
04/15/2022

Neural Structured Prediction for Inductive Node Classification

This paper studies node classification in the inductive setting, i.e., a...
research
02/17/2023

Creating generalizable downstream graph models with random projections

We investigate graph representation learning approaches that enable mode...

Please sign up or login with your details

Forgot password? Click here to reset