A rule-based strikingness measure is added to TKGR metrics to weight rare events higher, revealing that models weaken on striking events and ensemble gains come mostly from trivial fits.
Large language models as data augmenters for cold-start item recommendation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
TransFIR enables reasoning on temporal knowledge graphs for emerging entities by clustering them into semantic groups and borrowing interaction histories from similar known entities, yielding 28.6% average MRR gains.
citing papers explorer
-
Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning
A rule-based strikingness measure is added to TKGR metrics to weight rare events higher, revealing that models weaken on striking events and ensemble gains come mostly from trivial fits.
-
Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
TransFIR enables reasoning on temporal knowledge graphs for emerging entities by clustering them into semantic groups and borrowing interaction histories from similar known entities, yielding 28.6% average MRR gains.