AI RESEARCH
MSGCN: Multiplex Spatial Graph Convolution Network for Interlayer Link Weight Prediction
arXiv CS.LG
•
ArXi:2504.17749v2 Announce Type: replace Graph Neural Networks (GNNs) have been widely used for various learning tasks, ranging from node classification to link prediction. They have nstrated excellent performance in multiple domains involving graph-structured data. However, an important but less explored learning task is link weight prediction which is complex than binary link classification. Link weight prediction becomes even challenging when considering multilayer networks, where nodes can be connected across multiple layers.