Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction

Remington Kim; Yue Ning

doi:10.1007/978-3-030-96498-6_24

Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction

Remington Kim
, Yue Ning

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Knowledge graphs (KGs) are a way to model data involving intricate relations between a number of entities. Understanding the information contained in KGs and predicting what hidden relations may be present can provide valuable domain-specific knowledge. Thus, we use data provided by the 5th Annual Oak Ridge National Laboratory Smoky Mountains Computational Sciences Data Challenge 2 as well as auxiliary textual data processed with natural language processing techniques to form and analyze a COVID-19 KG of biomedical concepts and research papers. Moreover, we propose a recurrent graph convolutional network model that predicts both the existence of novel links between concepts in this COVID-19 KG and the time at which the link will form. We demonstrate our model’s promising performance against several baseline models. The utilization of our work can give insights that are useful in COVID-19-related fields such as drug development and public health. All code for our paper is publicly available at https://github.com/RemingtonKim/SMCDC2021.

Original language	English
Title of host publication	Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation - 21st Smoky Mountains Computational Sciences and Engineering, SMC 2021, Revised Selected Papers
Editors	[given-name]Jeffrey Nichols, [given-name]Arthur ‘Barney’ Maccabe, James Nutaro, Swaroop Pophale, Pravallika Devineni, Theresa Ahearn, Becky Verastegui
Pages	411-419
Number of pages	9
DOIs	https://doi.org/10.1007/978-3-030-96498-6_24
State	Published - 2022
Event	21st Smoky Mountains Computational Sciences and Engineering Conference, SMC 2021 - Virtual, Online Duration: 18 Oct 2021 → 20 Oct 2021

Publication series

Name	Communications in Computer and Information Science
Volume	1512 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	21st Smoky Mountains Computational Sciences and Engineering Conference, SMC 2021
City	Virtual, Online
Period	18/10/21 → 20/10/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

COVID-19 knowledge graph
Link prediction
Multi-task learning
Recurrent graph convolutional networks

Access to Document

10.1007/978-3-030-96498-6_24

Cite this

Kim, R., & Ning, Y. (2022). Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction. In J. Nichols, A. B. Maccabe, J. Nutaro, S. Pophale, P. Devineni, T. Ahearn, & B. Verastegui (Eds.), Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation - 21st Smoky Mountains Computational Sciences and Engineering, SMC 2021, Revised Selected Papers (pp. 411-419). (Communications in Computer and Information Science; Vol. 1512 CCIS). https://doi.org/10.1007/978-3-030-96498-6_24

Kim, Remington ; Ning, Yue. / Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction. Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation - 21st Smoky Mountains Computational Sciences and Engineering, SMC 2021, Revised Selected Papers. editor / [given-name]Jeffrey Nichols ; [given-name]Arthur ‘Barney’ Maccabe ; James Nutaro ; Swaroop Pophale ; Pravallika Devineni ; Theresa Ahearn ; Becky Verastegui. 2022. pp. 411-419 (Communications in Computer and Information Science).

@inproceedings{4d5aee502d9d4a97b8270fdd2e422640,

title = "Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction",

abstract = "Knowledge graphs (KGs) are a way to model data involving intricate relations between a number of entities. Understanding the information contained in KGs and predicting what hidden relations may be present can provide valuable domain-specific knowledge. Thus, we use data provided by the 5th Annual Oak Ridge National Laboratory Smoky Mountains Computational Sciences Data Challenge 2 as well as auxiliary textual data processed with natural language processing techniques to form and analyze a COVID-19 KG of biomedical concepts and research papers. Moreover, we propose a recurrent graph convolutional network model that predicts both the existence of novel links between concepts in this COVID-19 KG and the time at which the link will form. We demonstrate our model{\textquoteright}s promising performance against several baseline models. The utilization of our work can give insights that are useful in COVID-19-related fields such as drug development and public health. All code for our paper is publicly available at https://github.com/RemingtonKim/SMCDC2021.",

keywords = "COVID-19 knowledge graph, Link prediction, Multi-task learning, Recurrent graph convolutional networks",

author = "Remington Kim and Yue Ning",

note = "Publisher Copyright: {\textcopyright} 2022, Springer Nature Switzerland AG.; 21st Smoky Mountains Computational Sciences and Engineering Conference, SMC 2021 ; Conference date: 18-10-2021 Through 20-10-2021",

year = "2022",

doi = "10.1007/978-3-030-96498-6\_24",

language = "English",

isbn = "9783030964979",

series = "Communications in Computer and Information Science",

pages = "411--419",

editor = "[given-name]Jeffrey Nichols and Maccabe, \{[given-name]Arthur {\textquoteleft}Barney{\textquoteright}\} and James Nutaro and Swaroop Pophale and Pravallika Devineni and Theresa Ahearn and Becky Verastegui",

booktitle = "Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation - 21st Smoky Mountains Computational Sciences and Engineering, SMC 2021, Revised Selected Papers",

}

Kim, R & Ning, Y 2022, Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction. in J Nichols, AB Maccabe, J Nutaro, S Pophale, P Devineni, T Ahearn & B Verastegui (eds), Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation - 21st Smoky Mountains Computational Sciences and Engineering, SMC 2021, Revised Selected Papers. Communications in Computer and Information Science, vol. 1512 CCIS, pp. 411-419, 21st Smoky Mountains Computational Sciences and Engineering Conference, SMC 2021, Virtual, Online, 18/10/21. https://doi.org/10.1007/978-3-030-96498-6_24

Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction. / Kim, Remington; Ning, Yue.
Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation - 21st Smoky Mountains Computational Sciences and Engineering, SMC 2021, Revised Selected Papers. ed. / [given-name]Jeffrey Nichols; [given-name]Arthur ‘Barney’ Maccabe; James Nutaro; Swaroop Pophale; Pravallika Devineni; Theresa Ahearn; Becky Verastegui. 2022. p. 411-419 (Communications in Computer and Information Science; Vol. 1512 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction

AU - Kim, Remington

AU - Ning, Yue

PY - 2022

Y1 - 2022

N2 - Knowledge graphs (KGs) are a way to model data involving intricate relations between a number of entities. Understanding the information contained in KGs and predicting what hidden relations may be present can provide valuable domain-specific knowledge. Thus, we use data provided by the 5th Annual Oak Ridge National Laboratory Smoky Mountains Computational Sciences Data Challenge 2 as well as auxiliary textual data processed with natural language processing techniques to form and analyze a COVID-19 KG of biomedical concepts and research papers. Moreover, we propose a recurrent graph convolutional network model that predicts both the existence of novel links between concepts in this COVID-19 KG and the time at which the link will form. We demonstrate our model’s promising performance against several baseline models. The utilization of our work can give insights that are useful in COVID-19-related fields such as drug development and public health. All code for our paper is publicly available at https://github.com/RemingtonKim/SMCDC2021.

AB - Knowledge graphs (KGs) are a way to model data involving intricate relations between a number of entities. Understanding the information contained in KGs and predicting what hidden relations may be present can provide valuable domain-specific knowledge. Thus, we use data provided by the 5th Annual Oak Ridge National Laboratory Smoky Mountains Computational Sciences Data Challenge 2 as well as auxiliary textual data processed with natural language processing techniques to form and analyze a COVID-19 KG of biomedical concepts and research papers. Moreover, we propose a recurrent graph convolutional network model that predicts both the existence of novel links between concepts in this COVID-19 KG and the time at which the link will form. We demonstrate our model’s promising performance against several baseline models. The utilization of our work can give insights that are useful in COVID-19-related fields such as drug development and public health. All code for our paper is publicly available at https://github.com/RemingtonKim/SMCDC2021.

KW - COVID-19 knowledge graph

KW - Link prediction

KW - Multi-task learning

KW - Recurrent graph convolutional networks

UR - https://www.scopus.com/pages/publications/85127065654

UR - https://www.scopus.com/pages/publications/85127065654#tab=citedBy

U2 - 10.1007/978-3-030-96498-6_24

DO - 10.1007/978-3-030-96498-6_24

M3 - Conference contribution

AN - SCOPUS:85127065654

SN - 9783030964979

T3 - Communications in Computer and Information Science

SP - 411

EP - 419

BT - Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation - 21st Smoky Mountains Computational Sciences and Engineering, SMC 2021, Revised Selected Papers

A2 - Nichols, [given-name]Jeffrey

A2 - Maccabe, [given-name]Arthur ‘Barney’

A2 - Nutaro, James

A2 - Pophale, Swaroop

A2 - Devineni, Pravallika

A2 - Ahearn, Theresa

A2 - Verastegui, Becky

T2 - 21st Smoky Mountains Computational Sciences and Engineering Conference, SMC 2021

Y2 - 18 October 2021 through 20 October 2021

ER -

Kim R, Ning Y. Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction. In Nichols J, Maccabe AB, Nutaro J, Pophale S, Devineni P, Ahearn T, Verastegui B, editors, Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation - 21st Smoky Mountains Computational Sciences and Engineering, SMC 2021, Revised Selected Papers. 2022. p. 411-419. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-96498-6_24

Recurrent Multi-task Graph Convolutional Networks for COVID-19 Knowledge Graph Link Prediction

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this