RandAlign: A Parameter-Free Method for Regularizing Graph Convolutional Networks

arXiv:2404.09774v1 Announce Type: new
Abstract: Studies continually find that message-passing graph convolutional networks suffer from the over-smoothing issue. Basically, the issue of over-smoothing refers to the phenomenon that the learned embeddings for all nodes can become very similar to one another and therefore are uninformative after repeatedly applying message passing iterations. Intuitively, we can expect the generated embeddings become smooth asymptotically layerwisely, that is each layer of graph convolution generates a smoothed version of embeddings as compared to that generated …

abstract arxiv become cs.cv cs.lg embeddings free graph issue networks nodes studies type