KGFMs can predict links using observed half-links, with performance varying across four scenarios of half-link visibility in inference graphs.
D eep P ath: A Reinforcement Learning Method for Knowledge Graph Reasoning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CPR uses query-level conformal calibration over path scores and a PUCT-trained RCVNet to achieve valid coverage guarantees and smaller prediction sets in KGQA, reporting 45% higher empirical coverage and 52% smaller sets than prior conformal baselines.
citing papers explorer
-
Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models
KGFMs can predict links using observed half-links, with performance varying across four scenarios of half-link visibility in inference graphs.
-
Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
CPR uses query-level conformal calibration over path scores and a PUCT-trained RCVNet to achieve valid coverage guarantees and smaller prediction sets in KGQA, reporting 45% higher empirical coverage and 52% smaller sets than prior conformal baselines.