LiFTER predicts future links in continuous-time dynamic graphs with a signed sum of grounded temporal rule executions, matching neural baselines on historical-negative forecasting while providing exact, replayable evidence for every score.
Temporal graph networks for deep learning on dynamic graphs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LiFTER: A Grounded Neuro-Symbolic Microscope for Continuous-Time Dynamic Graph Forecasting
LiFTER predicts future links in continuous-time dynamic graphs with a signed sum of grounded temporal rule executions, matching neural baselines on historical-negative forecasting while providing exact, replayable evidence for every score.