Visualizing Graph Neural Networks With CorGIE : Corresponding a Graph to Its Embedding
Graph neural networks (GNNs) are a class of powerful machine learning tools that model node relations for making predictions of nodes or links. GNN developers rely on quantitative metrics of the predictions to evaluate a GNN, but similar to many other neural networks, it is difficult for them to und...
Veröffentlicht in: | IEEE transactions on visualization and computer graphics. - 1996. - 28(2022), 6 vom: 01. Juni, Seite 2500-2516 |
---|---|
1. Verfasser: | |
Weitere Verfasser: | , , |
Format: | Online-Aufsatz |
Sprache: | English |
Veröffentlicht: |
2022
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on visualization and computer graphics |
Schlagworte: | Journal Article Research Support, Non-U.S. Gov't |
Zusammenfassung: | Graph neural networks (GNNs) are a class of powerful machine learning tools that model node relations for making predictions of nodes or links. GNN developers rely on quantitative metrics of the predictions to evaluate a GNN, but similar to many other neural networks, it is difficult for them to understand if the GNN truly learns characteristics of a graph as expected. We propose an approach to corresponding an input graph to its node embedding (aka latent space), a common component of GNNs that is later used for prediction. We abstract the data and tasks, and develop an interactive multi-view interface called CorGIE to instantiate the abstraction. As the key function in CorGIE, we propose the K-hop graph layout to show topological neighbors in hops and their clustering structure. To evaluate the functionality and usability of CorGIE, we present how to use CorGIE in two usage scenarios, and conduct a case study with five GNN experts. Availability: Open-source code at https://github.com/zipengliu/corgie-ui/, supplemental materials & video at https://osf.io/tr3sb/ |
---|---|
Beschreibung: | Date Completed 08.06.2022 Date Revised 27.06.2022 published: Print-Electronic Citation Status MEDLINE |
ISSN: | 1941-0506 |
DOI: | 10.1109/TVCG.2022.3148197 |