Using SyPI time-series causal discovery to build an adjacency matrix improves out-of-distribution mobility forecasts compared to fixed baselines, but the evaluation lacks sparsity controls and error bars.
St- gin: An uncertainty quantification approach in traffic data imputation with spatio-temporal graph attention and bidirectional recurrent united neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Causal Adjacency Learning for Spatiotemporal Prediction Over Graphs
Using SyPI time-series causal discovery to build an adjacency matrix improves out-of-distribution mobility forecasts compared to fixed baselines, but the evaluation lacks sparsity controls and error bars.