Graph Neural Networks Designed for Different Graph Types: A Survey
Abstract: 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.
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: Added minor revisions of editor:
- added reference to Tab. 7
- improved writing and removed ambiguity in notation of Def. 3.2
- minor corrections in text of Definitions 3.3 and 3.7
Removed definitions of sets of all undirected/multi/attributed graphs because thanks to the minor revision of the editor we noticed they were not needed.
Moved around tables (within subsections) and deleted white space that was produced due to the changes in the review process.
Replaced the picture of the dog in Fig. 1 with the group's logo.
Added Acknowledgements.
Assigned Action Editor: ~Guillaume_Rabusseau1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 699
Loading