LABEL PROPAGATION ACROSS GRAPHS: NODE CLASSIFICATION USING GRAPH NEURAL TANGENT KERNELS

Artun Bayer, Arindam Chowdhury, Santiago Segarra

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Graph neural networks (GNNs) have achieved superior performance on node classification tasks in the last few years. Commonly, this is framed in a transductive semi-supervised learning setup wherein the entire graph - including the target nodes to be labeled - is available for training. Driven in part by scalability, recent works have focused on the inductive case where only the labeled portion of a graph is available for training. In this context, our current work considers a challenging inductive setting where a set of labeled graphs are available for training while the unlabeled target graph is completely separate, i.e., there are no connections between labeled and unlabeled nodes. Under the implicit assumption that the testing and training graphs come from similar distributions, our goal is to develop a labeling function that generalizes to unobserved connectivity structures. To that end, we employ a graph neural tangent kernel (GNTK) that corresponds to infinitely wide GNNs to find correspondences between nodes in different graphs based on both the topology and the node features. We augment the capabilities of the GNTK with residual connections and empirically illustrate its performance gains on standard benchmarks.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5483-5487
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Externally publishedYes
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
Duration: May 23 2022May 27 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period05/23/2205/27/22

Keywords

  • graph neural network
  • graph representation learning
  • neural tangent kernel
  • Node classification

Fingerprint

Dive into the research topics of 'LABEL PROPAGATION ACROSS GRAPHS: NODE CLASSIFICATION USING GRAPH NEURAL TANGENT KERNELS'. Together they form a unique fingerprint.

Cite this