Temporal Graph Networks combine memory modules and graph operators to learn on dynamic graphs as timed event sequences, outperforming prior methods on transductive and inductive tasks while unifying earlier models as special cases.
International Conference on Learning Representations , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
STOIC integrates STGNN point forecasting with tabular foundation model in-context learning for conformal prediction to quantify uncertainty in graph-structured energy time series.
Regime-stratified evaluation on traffic benchmarks shows TSFM accuracy and interval coverage collapse during transitions (MAE 11 mph vs 3 mph overall; coverage to 55%), hidden by free-flow dominance, with BMA augmentation recovering transition coverage.
GenTTP is a generalized predictor that learns to forecast network-wide travel times and flows for arbitrary route choice distributions rather than only typical daily patterns.
citing papers explorer
-
Temporal Graph Networks for Deep Learning on Dynamic Graphs
Temporal Graph Networks combine memory modules and graph operators to learn on dynamic graphs as timed event sequences, outperforming prior methods on transductive and inductive tasks while unifying earlier models as special cases.
-
Relational and Sequential Conformal Inference for Energy Time Series over Graphs via Foundation Models
STOIC integrates STGNN point forecasting with tabular foundation model in-context learning for conformal prediction to quantify uncertainty in graph-structured energy time series.
-
Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting
Regime-stratified evaluation on traffic benchmarks shows TSFM accuracy and interval coverage collapse during transitions (MAE 11 mph vs 3 mph overall; coverage to 55%), hidden by free-flow dominance, with BMA augmentation recovering transition coverage.
-
Generalising Travel Time Prediction To Varying Route Choices In Urban Networks
GenTTP is a generalized predictor that learns to forecast network-wide travel times and flows for arbitrary route choice distributions rather than only typical daily patterns.