DGAR uses diffusion-generated, model-guided historical entity distributions with adaptive replay to reduce catastrophic forgetting in temporal knowledge graph reasoning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning
DGAR uses diffusion-generated, model-guided historical entity distributions with adaptive replay to reduce catastrophic forgetting in temporal knowledge graph reasoning.