AdaTKG equips temporal knowledge graph entities with per-entity memories updated via a single shared learnable exponential moving average, allowing online adaptation and better reasoning on evolving facts.
Learning from history: Modeling temporal knowledge graphs with sequential copy-generation networks
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.AI 1years
2026 1verdicts
ACCEPT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning
AdaTKG equips temporal knowledge graph entities with per-entity memories updated via a single shared learnable exponential moving average, allowing online adaptation and better reasoning on evolving facts.