all AI news
ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization. (arXiv:2206.08181v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
Graph Neural Networks (GNNs) have attracted much attention due to their
ability in learning representations from graph-structured data. Despite the
successful applications of GNNs in many domains, the optimization of GNNs is
less well studied, and the performance on node classification heavily suffers
from the long-tailed node degree distribution. This paper focuses on improving
the performance of GNNs via normalization.
In detail, by studying the long-tailed distribution of node degrees in the
graph, we propose a novel normalization method for …
arxiv distribution graph graph neural networks lg networks neural networks normalization