A residual-aware attention block and spatial-disparity loss are reported to reduce prediction-error clustering across Chicago neighborhoods, but the gains are partly artifacts of training on the same metrics used for evaluation.
Adaptive graph convolutional recurrent network for traffic forecasting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Mitigating Spatial Disparity in Urban Prediction Using Residual-Aware Spatiotemporal Graph Neural Networks: A Chicago Case Study
A residual-aware attention block and spatial-disparity loss are reported to reduce prediction-error clustering across Chicago neighborhoods, but the gains are partly artifacts of training on the same metrics used for evaluation.