Limitations of Graph Neural Networks

Article: https://towardsdatascience.com/limitations-of-graph-neural-networks-2412fffe677

Some thoughts below:

  • We need injective node aggregation functions in order to guarantee that graphs that are different will be differentiated from one another.

This probably means that a simple sum isn't good enough and a mean won't cut it.

Pages that link here

Reading Bazaar
Interesting reads from my random walk over the internet