ReInc trains dynamic GNNs on large graphs up to 12.8x to 17.7x faster than DynaGraph and ESDGNN by reusing cached aggregations, incremental delta-based updates, and a communication-free snapshot placement.
One trillion edges: Graph processing at facebook-scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ReInc: Scaling Training of Dynamic Graph Neural Networks
ReInc trains dynamic GNNs on large graphs up to 12.8x to 17.7x faster than DynaGraph and ESDGNN by reusing cached aggregations, incremental delta-based updates, and a communication-free snapshot placement.