Weanalyzegraphsmoothingwith meanaggregation,whereeachnodesuccessively 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 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, forconnected graphs, thenodefeatures become constant across the whole graph.

Our main contribution is the first bias-variance bound for the problem of learning Gaussian mixtures with streaming data.

In this paper, we address the problems of identifying linear structural equation models and discovering the constraints they imply.