no code implementations • 6 Sep 2021 • Marinos Poiitis, Pavlos Sermpezis, Athena Vakali
In a different GRL approach, spectral methods based on graph filtering have emerged addressing over smoothing; however, up to now, they employ traditional neural networks that cannot efficiently exploit the structure of graph data.
1 code implementation • NeurIPS 2021 • Andreas Loukas, Marinos Poiitis, Stefanie Jegelka
This work explores the Benevolent Training Hypothesis (BTH) which argues that the complexity of the function a deep neural network (NN) is learning can be deduced by its training dynamics.