T3DM couples an LSTM-predicted entity-distribution auxiliary task at test time with a GAN-based negative sampler to improve temporal knowledge graph link prediction.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
T3DM: Test-Time Training-Guided Distribution Shift Modelling for Temporal Knowledge Graph Reasoning
T3DM couples an LSTM-predicted entity-distribution auxiliary task at test time with a GAN-based negative sampler to improve temporal knowledge graph link prediction.