COMM-RAND creates community-aware randomized mini-batches for GNN training, cutting training time by 1.8x on average with negligible accuracy loss.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
COMM-RAND creates community-aware randomized mini-batches for GNN training, cutting training time by 1.8x on average with negligible accuracy loss.