WaveGSSM: Graph Wave State Space Models for Propagating Spatio-Temporal Patterns
WaveGSSM is introduced, a second-order graph state-space model that maintains two coupled latent states at each node, one for the current pattern and one for its temporal rate of change, and achieves the best mean performance across the temporal-graph benchmarks and global weather forecasting.
Jun-You Zhu, Fen-Ying Cai, Pin Xiong et al.
· 0 citations