
To explain GNNs, we first need to know what type of explanations we need. Recently, several approaches are proposed to explain GNN models, such as XGNN 3, GNNExplainer 4, PGExplainer 5, and SubgraphX. To demystify such black-boxes, we need to study the explainability of GNNs. Without reasoning the prediction procedures of GNNs, we do not understand GNN models and do not know whether the models work in our expected way, thus preventing their use in critical applications pertaining to fairness, privacy, and safety. Thank you, Fontes.Deep graph models are usually treated as black-boxes and lacking explainability. Fontes has proved the forum is fair and does not lean toward a language. And, now, because of Fontes, we know the forum is exactly what it is presented to be. He had 186 views on his Master Archer, 186 views with his Pope Battle XIII, and 198 views on his Orella Resin Statue. These works rotate based on popularity(of recent views?), so if any of them stay up for awhile, it's an achievement.

However, Congrats to Fontes! He is on the front page with several works. So you can scroll through users to find users who you like their art but don't post often.

There's ten users a page, and 649 pages at the moment. There's also a User List, which may be based on the alphabet or phonetics. Additionally, if you happen to create a work or finish your work in another software, you won't have the event file, but you'll still have the image to post. When you post a work, you even have the option of posting an event file or an image, so you have some control over what the users see. The majority of the users are Japanese, though some English users are floating around here or there.


You can make a profile, pick favorites to play later, pick artists who are your favorites so you can see more work they produce, download event files uploaded by other artists to learn from them, and post your own work. This is the community place ( ) for portal graphics software.
