SGBGC compresses graphs by grouping same-label nodes into granular-balls and training GNNs on the coarsened graph, but its evaluation leaks test labels into the coarsening step.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training
SGBGC compresses graphs by grouping same-label nodes into granular-balls and training GNNs on the coarsened graph, but its evaluation leaks test labels into the coarsening step.