Online Adaptive Graph Neural Networks

Master Thesis (2024)
Author(s)

A.J. Jeleniewski (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Elvin Isufi – Mentor (TU Delft - Multimedia Computing)

Mohammad Sabbaqi – Graduation committee member (TU Delft - Multimedia Computing)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2024
Language
English
Graduation Date
04-07-2024
Awarding Institution
Delft University of Technology
Programme
Computer Science | Artificial Intelligence
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Analyzing and forecasting multivariate time series using networks is interesting in traffic, energy consumption, or financial forecasting applications. The main challenge is to capture both spatial and temporal dependencies in the data alongside the dynamics of the network itself. Graph Neural Networks (GNNs) have shown reliable performance in network-based data by modeling the connections as a graph. GNNs, using temporal and recurrent structures, are further developed as a prominent tool for processing multivariate time series. However, the dynamics of the network, the evolution of the network over time, and its effect on the data should be studied more. Recent works augment temporal GNNs with graph learning modules to account for the changes in the network; however, often, these methods do not consider the dynamics directly, and all of them stop the graph changing after the training phase. This thesis focuses on an online graph adapting approach to deal with the dynamic data over networks. The proposed method is a hybrid model consisting of a temporal GNN inspired by the physics of dynamic networks, trains its parameters during the training phase, and adapts the graph with the stream of temporal data online. The experiments study the graph adaptation module's role on various benchmark datasets in forecasting tasks, such as traffic, windmill energy, and financial forecasting.

Files

License info not available