AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing. (arXiv:2304.07014v1 [cs.LG])

Graph Convolutional Network (GCN) with the powerful capacity to explore
graph-structural data has gained noticeable success in recent years.
Nonetheless, most of the existing GCN-based models suffer from the notorious
over-smoothing issue, owing to which shallow networks are extensively adopted.
This may be problematic for complex graph datasets because a deeper GCN should
be beneficial to propagating information across remote neighbors. Recent works
have devoted effort to addressing over-smoothing problems, including
establishing residual connection structure or fusing predictions from
multi-layer …

arxiv capacity data datasets graph information issue neighbors network networks neural networks predictions success