Random Walk Diffusion
A process that generates correlated signals on graph structures, incorporating graph-structural information into the data-generation prior through random walks.
Timeline (last 90 days)
The paper uses random-walk diffusion to incorporate sampled road topologies into the synthetic task prior, enabling the model to learn graph-coupled dynamic patterns during pretraining.
The idea of introducing random-walk diffusion into synthetic priors is also of reference value for other time series tasks with graph structure (such as energy networks and meteorological monitoring).
All Facts (2)
The paper uses random-walk diffusion to incorporate sampled road topologies into the synthetic task prior, enabling the model to learn graph-coupled dynamic patterns during pretraining.
50%UnverifiedThe idea of introducing random-walk diffusion into synthetic priors is also of reference value for other time series tasks with graph structure (such as energy networks and meteorological monitoring).
50%