A Recurrent Graph Neural Network for Multi-relational Data

Vassilis N. Ioannidis, Antonio G. Marques, Georgios B Giannakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

Abstract

The era of data deluge has sparked the interest in graph-based learning methods in a number of disciplines such as sociology, biology, neuroscience, or engineering. In this paper, we introduce a graph recurrent neural network (GRNN) for scalable semi-supervised learning from multi-relational data. Key aspects of the novel GRNN architecture are the use of multi-relational graphs, the dynamic adaptation to the different relations via learnable weights, and the consideration of graph-based regularizers to promote smoothness and alleviate over-parametrization. Our ultimate goal is to design a powerful learning architecture able to: discover complex and highly non-linear data associations, combine (and select) multiple types of relations, and scale gracefully with respect to the size of the graph. Numerical tests with real datasets corroborate the design goals and illustrate the performance gains relative to competing alternatives.

Original languageEnglish (US)
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages8157-8161
Number of pages5
ISBN (Electronic)9781479981311
DOIs
StatePublished - May 2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: May 12 2019May 17 2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period5/12/195/17/19

Bibliographical note

Funding Information:
The work in this paper has been supported by USA NSF grants 171141, 1500713, and 1442686, and by the Spanish grants MINECO KLINILYCS (TEC2016-75361-R) and Instituto de Salud Carlos III DTS17/00158. 1Many works in the literature refer to these graphs as multi-layer graphs.

Keywords

  • Deep neural networks
  • graph recurrent neural networks
  • graph signals
  • multi-relational graphs

Fingerprint Dive into the research topics of 'A Recurrent Graph Neural Network for Multi-relational Data'. Together they form a unique fingerprint.

Cite this