https://thegradient.pub/graph-neural-networks-beyond-message-passing-and-weisfeiler-lehman/
Beyond Message Passing: a Physics-Inspired Paradigm for Graph Neural Networks
Michael Bronstein
07.May.2022
“…the “node and edge-centric” mindset of current graph deep learning schemes imposes strong limitations… we propose physics-inspired “continuous” learning models that open up a new trove of tools from the fields of differential geometry, algebraic topology, and differential equations…”