A Gentle Introduction to Graph Neural Networks (2021)

(distill.pub)

354 points misonic | 2 comments | 20 Dec 24 04:10 UTC | HN request time: 0.438s | source

Show context

helltone ◴[20 Dec 24 07:12 UTC] No.42468950[source]▶

It seems GNNs operate on a fixed topology. What if I want to approximate some transformation of the topology of the graph? For example learning how to layout a graph, or converting program abstract syntax trees to data flow graphs.

replies(2): >>42469251 #>>42472310 #

1. igorkraw ◴[20 Dec 24 08:24 UTC] No.42469251[source]▶

>>42468950 #

The whole point of GNNs is that they generalize to arbitrary topologies by explicitly conditioning the idea of "neighbours" on the graph specifying the topology. Graph layout has been tried here https://github.com/limbo018/DREAMPlace to great fanfare although there is recent drama about it https://www.semanticscholar.org/paper/The-False-Dawn%3A-Reev... . Graph transformations are a thing as well https://arxiv.org/abs/2012.01470 but it's a tricky problem because you implicitly need to solve the graph matching problem

replies(1): >>42469447 #

2. Xmd5a ◴[20 Dec 24 09:17 UTC] No.42469447[source]▶

>>42469251 (TP) #

Graph layout is extremely interesting for infographics, since a handmade graph will almost always beat what tools such as graphviz can come up with (and I'm not even mentioning algorithms that go beyond Sugiyama's for which there is only a paper).

Any progress on this front ?

↑