Scaling Graph Neural Networks to Twitter-scale (w/ Emanuele Rossi interview)

This is an interview with Emanuele Rossi, who is an ML researcher at Twitter and Phd student with Michael Bronstein that focuses on applying GNNs to large scale, dynamic graphs. Follow the discussion here: And you can find more from Emanuele at: SIGN paper: Mailing List: Discord Server: Blog: Patreon: Chapters 00:00 Intro 01:15 Interview start 06:01 Industrial challenges 07:46 Academic vs Industrial graphs 10:56 Graph sampling 13:04 SIGN intro 13:56 Problems with deeper GNNs 16:27 Oversmoothing problem 18:18 Convolution Operators 21:01 Expressiveness of operators 24:30 Triangle-based operators 29:05 Simple GCN 31:28 SIGN summary 32:43 Finding good operators 34:15 Evolving g