ScaDyG proposes a decoupled, step-wise exponential time encoding with hypernetwork aggregation for scalable dynamic graph learning, but the key proof of equivalence with composite exponential message passing is invalid as stated.
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
REJECT 1representative citing papers
citing papers explorer
-
ScaDyG:A New Paradigm for Large-scale Dynamic Graph Learning
ScaDyG proposes a decoupled, step-wise exponential time encoding with hypernetwork aggregation for scalable dynamic graph learning, but the key proof of equivalence with composite exponential message passing is invalid as stated.