Skip to main navigation Skip to search Skip to main content

Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification

  • Technical University of Munich
  • UIC ECE-CSN-Lab

Research output: Contribution to conferencePaperpeer-review

5 Scopus citations

Abstract

Node features and structural information of a graph are both crucial for semi-supervised node classification problems. A variety of graph neural network (GNN) based approaches have been proposed to tackle these problems, which typically determine output labels through feature aggregation. This can be problematic, as it implies conditional independence of output nodes given hidden representations, despite their direct connections in the graph. To learn the direct influence among output nodes in a graph, we propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field. It contains explicit pairwise factors to model output-output relations and uses a GNN backbone to model input-output relations. To balance model complexity and expressivity, the pairwise factors have a shared component and a separate scaling coefficient for each edge. We apply the EM algorithm to train our model, and utilize a star-shaped piecewise likelihood for the tractable surrogate objective. We conduct experiments on various datasets, which shows that our model can effectively improve the performance for semi-supervised node classification on graphs.

Original languageEnglish
Pages1979-1987
Number of pages9
StatePublished - 2021
Event37th Conference on Uncertainty in Artificial Intelligence, UAI 2021 - Virtual, Online
Duration: 27 Jul 202130 Jul 2021

Conference

Conference37th Conference on Uncertainty in Artificial Intelligence, UAI 2021
CityVirtual, Online
Period27/07/2130/07/21

Fingerprint

Dive into the research topics of 'Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification'. Together they form a unique fingerprint.

Cite this