The Flow has not summarised this story yet — read it at arXiv AI.
arXiv:2605.25004v2 Announce Type: replace Abstract: Inferring network-wide traffic states from sparse observations with high accuracy and trustworthy uncertainty quantification is essential for intel...
arXiv:2505. 13102v4 Announce Type: replace-cross Abstract: Unlike conventional "black-box" transformers with classical self-attention mechanism, we build a lightweight and interpretable transformer-like neural net by unrolling a mixed-graph-based optimization algorithm to forecast traffic with spatial and temporal dimensions.
arXiv:2606. 19138v1 Announce Type: new Abstract: Neural Controlled Differential Equations (NCDE) provide a powerful continuous-time framework for forecasting time series, but standard graph-based extensions typically learn spatial structure purely from data, even in settings where a directed graph structure is known a priori.
RiskTraf introduces a risk-extrapolated residual learning approach for multi-variate traffic flow prediction, leveraging raw flow, speed, and occupancy data from the new PEMSB-3V benchmark. The method freezes a trained spatio-temporal backbone and adds a lightweight residual head that learns from historical speed and occupancy to correct flow predictions across different traffic regimes. Experiments show consistent improvements over various backbones and outperform existing debiasing and distribution-shift adaptation techniques.
SiST‑GNN introduces a simultaneous spatial‑temporal message‑passing framework for dynamic graph neural networks, fusing per‑node temporal embeddings with spatial aggregation in a single operation. By maintaining a recurrent hidden state per node and treating it as a cross‑time edge, the model jointly reasons over topology and evolution. Experiments on link‑prediction and node‑classification benchmarks show significant improvements over prior methods, achieving up to 158% gains in live‑update link prediction and outperforming discrete‑time baselines by 7–23% in dynamic node classification.
The paper introduces a gated graph attention network (GAT) to better explain spatial information flow in short‑term traffic forecasting models. By adding a gate that learns how much of a sensor’s updated state comes from its neighbors versus itself, the authors can progressively withdraw neighbor information and observe its impact on accuracy. Applied to the ST‑MetaNet architecture on data from 498 loop detectors in England, the gated GAT shows that neighbor influence is higher for busy sensors, improves accuracy slightly with mild regularisation, and reveals that the two GAT layers are largely redundant.