Hao Dong, Pengfei Wang, Yanjie Fu, Denghui Zhang, Pengyang Wang, Dingqi Yang, Yicheng Zhou
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Urban traffic speed prediction aims to estimate the future traffic speed for improving urban transportation services. Enormous efforts have been made to exploit Graph Neural Networks (GNNs) for modeling spatial correlations and temporal dependencies of traffic speed evolving patterns, regularized by graph topology. While achieving promising results, current traffic speed prediction methods still suffer from ignoring topology-free patterns, which cannot be captured by GNNs. To tackle this challenge, we propose a generic model for enabling the current GNN-based methods to preserve topology-free patterns. Specifically, we first develop a Dual Cross-Scale Transformer (DCST) architecture, including a Spatial Transformer and a Temporal Transformer, to preserve the crossscale topology-free patterns and associated dynamics, respectively. Then, to further integrate both topology-regularized/-free patterns, we propose a distillation-style learning framework, in which the existing GNN-based methods are considered as the teacher model, and the proposed DCST architecture is considered as the student model. The teacher model would inject the learned topologyregularized patterns into the student model for integrating topology-free patterns. The extensive experimental results demonstrated the effectiveness of our methods.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.16992")
get_code_for_paper("2406.16992")
have("2406.16992")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.16992.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.16992)
Connect an agent — have() is free.