CRAFT replaces memory and aggregation with learnable node embeddings and destination-to-source-neighbor cross-attention, improving future link prediction on most of 17 temporal graph benchmarks.
Hot: Higher-order dynamic graph representation learning with efficient transformers
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
background 1representative citing papers
citing papers explorer
-
Future Link Prediction Without Memory or Aggregation
CRAFT replaces memory and aggregation with learnable node embeddings and destination-to-source-neighbor cross-attention, improving future link prediction on most of 17 temporal graph benchmarks.