T-GRAB, a set of three synthetic temporal-graph tasks, shows that no current TGNN reliably does counting, delayed cause-effect, or long-range spatio-temporal reasoning.
Tempo- ral graph benchmark for machine learning on temporal graphs
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.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs
T-GRAB, a set of three synthetic temporal-graph tasks, shows that no current TGNN reliably does counting, delayed cause-effect, or long-range spatio-temporal reasoning.