IMPaCT reweights graph message passing to align first and second moments across chronological train/test splits, reporting accuracy gains on ogbn-mag and a theoretical W1 bound.
Data for t = 2018 and t = 2019 were excluded, and no scaling corrections were applied
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
-
IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphs
IMPaCT reweights graph message passing to align first and second moments across chronological train/test splits, reporting accuracy gains on ogbn-mag and a theoretical W1 bound.