Skip to main content

Research Repository

Advanced Search

Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions

Bonner, Stephen; Atapour-Abarghouei, Amir; Jackson, Phillip; Brennan, John; Kureshi, Ibad; Theodoropoulos, Georgios; McGough, Stephen; Obara, Boguslaw

Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions Thumbnail


Authors

Stephen Bonner

Phillip Jackson

John Brennan

Ibad Kureshi

Georgios Theodoropoulos

Stephen McGough

Boguslaw Obara



Abstract

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently disregarded during the learning process, resulting in suboptimal performance on certain temporal inference tasks. To combat this, we introduce Temporal Neighbourhood Aggregation (TNA), a novel vertex representation model architecture designed to capture both topological and temporal information to directly predict future graph states. Our model exploits hierarchical recurrence at different depths within the graph to enable exploration of changes in temporal neighbourhoods, whilst requiring no additional features or labels to be present. The final vertex representations are created using variational sampling and are optimised to directly predict the next graph in the sequence. Our claims are supported by experimental evaluation on both real and synthetic benchmark datasets, where our approach demonstrates superior performance compared to competing methods, outperforming them at predicting new temporal edges by as much as 23% on real-world datasets, whilst also requiring fewer overall model parameters.

Citation

Bonner, S., Atapour-Abarghouei, A., Jackson, P., Brennan, J., Kureshi, I., Theodoropoulos, G., …Obara, B. (2019). Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions. In 2019 IEEE International Conference on Big Data (Big Data) (5336-5345). https://doi.org/10.1109/bigdata47090.2019.9005545

Conference Name IEEE International Conference on Big Data (Deep Graph Learning: Methodologies and Applications)
Conference Location Los Angeles, CA, USA
Start Date Dec 9, 2019
End Date Dec 12, 2019
Online Publication Date Feb 23, 2020
Publication Date 2019
Deposit Date Nov 5, 2019
Publicly Available Date Mar 29, 2024
Publisher Institute of Electrical and Electronics Engineers
Pages 5336-5345
Book Title 2019 IEEE International Conference on Big Data (Big Data).
DOI https://doi.org/10.1109/bigdata47090.2019.9005545

Files

Accepted Conference Proceeding (526 Kb)
PDF

Copyright Statement
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.





You might also like



Downloadable Citations