Temporal-aware structure-semantic-coupled graph network for traffic forecasting

Mao Chen, Liangzhe Han, Yi Xu, Tongyu Zhu, Jibin Wang, Leilei Sun

Abstract: Highlights•Graph indistinguishability prevents accurate traffic forecasting.•The Self-Sampling method effectively captures various temporal dependencies.•Structural and semantic learning helps to extract inherent graph features.•Sparse graph construction enhances interpretable and explicit graph learning.•Discriminative graph learning outperforms previous methods in forecasting.