Temporal Graph Offset Reconstruction: Towards Temporally Robust Graph Representation Learning

Bonner，Stephen1; Brennan，John1; Kureshi，Ibad4; Theodoropoulos，Georgios3; McGough，Andrew Stephen2; Obara，Boguslaw1

10.1109/BigData.2018.8622636

2019-01-22

Proceedings - 2018 IEEE International Conference on Big Data, Big Data 2018

3737-3746

Seattle, WA, United states

Institute of Electrical and Electronics Engineers Inc.

Graphs are a commonly used construct for representing relationships between elements in complex high dimensional datasets. Many real-world phenomenon are dynamic in nature, meaning that any graph used to represent them is inherently temporal. However, many of the machine learning models designed to capture knowledge about the structure of these graphs ignore this rich temporal information when creating representations of the graph. This results in models which do not perform well when used to make predictions about the future state of the graph - especially when the delta between time stamps is not small. In this work, we explore a novel training procedure and an associated unsupervised model which creates graph representations optimised to predict the future state of the graph. We make use of graph convo-lutional neural networks to encode the graph into a latent representation, which we then use to train our temporal offset reconstruction method, inspired by auto-encoders, to predict a later time point - multiple time steps into the future. Using our method, we demonstrate superior performance for the task of future link prediction compared with none-temporal state-of-the-art baselines. We show our approach to be capable of outperforming non-temporal baselines by 38% on a real world dataset.

dynamic graphs graph representation learning

非南科大

英语

EI

Nvidia[]

20191106616391

Big data ; Forecasting

Data Processing and Image Processing:723.2

2-s2.0-85062599093

Scopus

1.Department of Computer Science,Durham University,Durham,United Kingdom
2.School of Computing,Newcastle University,Newcastle,United Kingdom
3.School of Computer Science and Engineering,SUSTech,Shenzhen,China
4.InlecomSystems,Brussels,Belgium

Bonner，Stephen,Brennan，John,Kureshi，Ibad,et al. Temporal Graph Offset Reconstruction: Towards Temporally Robust Graph Representation Learning[C]:Institute of Electrical and Electronics Engineers Inc.,2019:3737-3746.