Stop Thinking, Just Do!

Sung-Soo Kim's Blog

Limitations of Graph Neural Networks


15 April 2021

Article Source

Limitations of Graph Neural Networks


One essential task to consider before we conduct machine learning on graphs is to find an appropriate way to represent the graphs. What are the factors that will affect our choices as to the representations? In this video, we’ll be looking at the different approaches to abstracting graphs: directed vs. undirected, weighted vs. unweighted, homogeneous vs bipartite, and so on.

comments powered by Disqus