TI-ODE decomposes graph ODE evolution into time-dependent learnable interaction basis functions, outperforming prior methods on dynamic graph attribute prediction and showing greater robustness.
IEEE Transactions on Knowledge and Data Engineering 38, 1159–1173
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Time-varying Interaction Graph ODE for Dynamic Graph Representation Learning
TI-ODE decomposes graph ODE evolution into time-dependent learnable interaction basis functions, outperforming prior methods on dynamic graph attribute prediction and showing greater robustness.