Propagation with Adaptive Mask then Training for Node Classification on Attributed Networks. (arXiv:2206.10142v2 [cs.LG] UPDATED)

Node classification on attributed networks is a semi-supervised task that is
crucial for network analysis. By decoupling two critical operations in Graph
Convolutional Networks (GCNs), namely feature transformation and neighborhood
aggregation, some recent works of decoupled GCNs could support the information
to propagate deeper and achieve advanced performance. However, they follow the
traditional structure-aware propagation strategy of GCNs, making it hard to
capture the attribute correlation of nodes and sensitive to the structure noise
described by edges whose two endpoints …

arxiv classification lg networks node training