Not too little, not too much: a theoretical analysis of graph (over)smoothing. (arXiv:2205.12156v1 [stat.ML])

We analyze graph smoothing with \emph{mean aggregation}, where each node
successively receives the average of the features of its neighbors. Indeed, it
has quickly been observed that Graph Neural Networks (GNNs), which generally
follow some variant of Message-Passing (MP) with repeated aggregation, may be
subject to the \emph{oversmoothing} phenomenon: by performing too many rounds
of MP, the node features tend to converge to a non-informative limit. In the
case of mean aggregation, for connected graphs, the node features become
constant …

analysis arxiv graph ml