The survey paper, entitled Graph Neural Networks Designed for Different Graph Types: A Survey, has been accepted for publication in Transactions on Machine Learning Research. This is a joint effort of the entire GAIN group based at IES with members Josephine Thomas, Alice Moallemy-Oureh, Silvia Beddar-Wiesing, and Clara Holzhüter.

The content of the article:

Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems. For this purpose, they can be defined as many different types which suitably reflect the individual contexts of the represented problem. To address cutting-edge problems based on graph data, the research field of Graph Neural Networks (GNNs) has emerged. Despite the field’s youth and the speed at which new models are developed, many recent surveys have been published to keep track of them. Nevertheless, it has not yet been gathered which GNN can process what kind of graph types. In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties. We consider GNNs operating on static and dynamic graphs of different structural constitutions, with or without node or edge attributes. Moreover, we distinguish between GNN models for discrete-time or continuous-time dynamic graphs and group the models according to their architecture. We find that there are still graph types that are not or only rarely covered by existing GNN models. We point out where models are missing and give potential reasons for their absence.

The article can be found here: https://openreview.net/pdf?id=h4BYtZ79uy