Domain adversarial graph neural network with cross-city graph structure learning for traffic prediction

Xiaocao Ouyang, Yan Yang, Yiling Zhang, Wei Zhou, Jihong Wan, Shengdong Du

Abstract: Highlights•A novel DAGN with cross-city graph structure learning is proposed.•First to consider inter-city node-wise adjacencies for knowledge transfer.•CCGSL captures cross-city node correlations, guided by reconstruction loss.•STA extracts domain-invariant features, GSTA adapts global aggregation.•Experiments show our model surpasses SOTA in traffic flow and speed prediction.