NeurIPS'22 "Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective"
with Haoteng Yin, Junteng Jia, Austin R. Benson, Pan Li
This work tries to establish the connection between Bayesian inference over a graphical model and Graph neural networks. With such a connection, we are able to measure the values of nonlinear operations in GNNs for the node classification task. We obtain a “negative” result: When node attributes are not very...
[Read More]